Langfuse MCP Servers
Available MCP servers
Server navigation
Langfuse Cloud MCP
getPromptgetPromptUnresolvedlistPromptscreateTextPromptcreateChatPromptupdatePromptLabelslistObservationsgetObservationgetObservationFieldSchemagetObservationFilterSchemagetObservationFilterValueslistAnnotationQueuescreateAnnotationQueuegetAnnotationQueuelistAnnotationQueueItemsgetAnnotationQueueItemcreateAnnotationQueueItemupdateAnnotationQueueItemdeleteAnnotationQueueItemcreateAnnotationQueueAssignmentdeleteAnnotationQueueAssignmentcreateCommentlistCommentsgetCommentupsertDatasetlistDatasetsgetDatasetupsertDatasetItemlistDatasetItemsgetDatasetItemdeleteDatasetItemcreateDatasetRunItemlistDatasetRunItemslistDatasetRunsgetDatasetRundeleteDatasetRungetHealthlistScoresgetScorecreateScorelistScoreConfigsgetScoreConfigcreateScoreConfigupdateScoreConfigdeleteScoreConfigqueryMetricsgetMetricsSchemalistModelscreateModelgetModeldeleteModelgetMedialistEvaluatorsgetEvaluatorupsertEvaluatorlistEvaluationRulesgetEvaluationRulecreateEvaluationRuleupdateEvaluationRuledeleteEvaluationRule
Langfuse Cloud MCP
Authenticated project-scoped MCP server for Langfuse Cloud projects.
https://cloud.langfuse.com/api/public/mcpAPI stability
This MCP server is self-describing. Clients should dynamically inspect available tools and schemas rather than assuming a static interface.
Tool availability and schemas may evolve over time, including the addition, removal, or modification of tools and fields. Clients are expected to tolerate schema changes and refresh capabilities dynamically.
Cloud EU
https://cloud.langfuse.com/api/public/mcp
Cloud US
https://us.cloud.langfuse.com/api/public/mcp
Cloud Japan
https://jp.cloud.langfuse.com/api/public/mcp
HIPAA US
https://hipaa.cloud.langfuse.com/api/public/mcp
Self-Hosted
https://your-domain.com/api/public/mcp
Local Development
http://localhost:3000/api/public/mcp
Client setup
Cursor mcp.json
json
{
"mcpServers": {
"langfuse-cloud": {
"url": "https://cloud.langfuse.com/api/public/mcp",
"headers": {
"Authorization": "Basic <base64(LANGFUSE_PUBLIC_KEY:LANGFUSE_SECRET_KEY)>"
}
}
}
}Tools
getPrompt
Fetch a specific prompt by name with optional label or version parameter. Retrieval options: - label: Get prompt with specific label (e.g., 'production', 'staging') - version: Get specific version number (e.g., 1, 2, 3) - neither: Returns 'latest' version by default Note: label and version are mutually exclusive. Returns full prompt content with resolved dependencies.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 255,
"description": "The name of the prompt"
},
"label": {
"description": "Label to retrieve (e.g., \"production\", \"staging\"). Defaults to \"latest\".",
"type": "string",
"minLength": 1,
"maxLength": 36,
"pattern": "^[a-z0-9_\\-.]+$"
},
"version": {
"description": "Specific version number to retrieve (e.g., 1, 2, 3)",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"name"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getPrompt",
"arguments": {
"name": "string",
"label": "string",
"version": 1
}
}
}getPromptUnresolved
Fetch a specific prompt by name with optional label or version parameter WITHOUT resolving dependencies. Returns the raw prompt content with dependency tags intact. Useful for: - Understanding prompt composition/stacking before resolution - Debugging prompt dependencies - Analyzing the dependency graph structure Retrieval options: - label: Get prompt with specific label (e.g., 'production', 'staging') - version: Get specific version number (e.g., 1, 2, 3) - neither: Returns 'latest' version by default Note: label and version are mutually exclusive. To get resolved prompts, use the 'getPrompt' tool instead.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 255,
"description": "The name of the prompt"
},
"label": {
"description": "Label to retrieve (e.g., \"production\", \"staging\"). Defaults to \"latest\".",
"type": "string",
"minLength": 1,
"maxLength": 36,
"pattern": "^[a-z0-9_\\-.]+$"
},
"version": {
"description": "Specific version number to retrieve (e.g., 1, 2, 3)",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"name"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getPromptUnresolved",
"arguments": {
"name": "string",
"label": "string",
"version": 1
}
}
}listPrompts
List and filter prompts in the project. Returns metadata including versions, labels, tags, last updated timestamp, and prompt type. Optional filters: - name: Filter by exact prompt name - label: Filter by label on any version - tag: Filter by tag - fromUpdatedAt: Filter prompts updated at or after this timestamp - toUpdatedAt: Filter prompts updated at or before this timestamp Pagination: page (default: 1), limit (default: 50, max: 100)
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"description": "Filter by exact prompt name match",
"type": "string",
"minLength": 1,
"maxLength": 255
},
"label": {
"description": "Filter by label (e.g., 'production', 'staging')",
"type": "string",
"minLength": 1,
"maxLength": 36,
"pattern": "^[a-z0-9_\\-.]+$"
},
"tag": {
"description": "Filter by tag (e.g., 'experimental', 'v1')",
"type": "string"
},
"fromUpdatedAt": {
"description": "Filter prompts updated at or after this timestamp (ISO 8601 with timezone, e.g. 2026-02-02T00:00:00Z)",
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"toUpdatedAt": {
"description": "Filter prompts updated at or before this timestamp (ISO 8601 with timezone, e.g. 2026-02-02T00:00:00Z)",
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"page": {
"default": 1,
"description": "Page number for pagination (default: 1)",
"type": "integer",
"minimum": 1,
"maximum": 9007199254740991
},
"limit": {
"default": 50,
"description": "Number of items to return (1-100, default: 50)",
"type": "integer",
"minimum": 1,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listPrompts",
"arguments": {
"limit": 50,
"page": 1,
"fromUpdatedAt": "2026-05-15T12:00:00.000Z",
"label": "string",
"name": "string",
"tag": "string",
"toUpdatedAt": "2026-05-15T12:00:00.000Z"
}
}
}createTextPrompt
Create a new text prompt version in Langfuse. Important: - Prompts are immutable - cannot modify existing versions - To update content, create a new version - To promote to production, use updatePromptLabels - Labels are unique across versions - Use {{variable_name}} syntax for dynamic content Accepts: name, prompt (string), optional labels, config, tags, commitMessage
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 255,
"description": "The name of the prompt"
},
"prompt": {
"type": "string",
"description": "The prompt text content (supports {{variables}})"
},
"labels": {
"description": "Labels to assign (e.g., ['production', 'staging'])",
"type": "array",
"items": {
"type": "string"
}
},
"config": {
"description": "Optional JSON config (e.g., {model: 'gpt-4', temperature: 0.7})",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"tags": {
"description": "Optional tags for organization (e.g., ['experimental', 'v2'])",
"type": "array",
"items": {
"type": "string"
}
},
"commitMessage": {
"description": "Optional commit message describing the changes",
"type": "string"
}
},
"required": [
"name",
"prompt"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createTextPrompt",
"arguments": {
"name": "string",
"prompt": "string",
"commitMessage": "string",
"config": {
"property": {}
},
"labels": [
"string"
],
"tags": [
"string"
]
}
}
}createChatPrompt
Create a new chat prompt version in Langfuse. Chat prompts are arrays of messages with roles and content. Important: - Prompts are immutable - cannot modify existing versions - To update content, create a new version - To promote to production, use updatePromptLabels - Labels are unique across versions Message roles: system (instructions), user (input, can contain {{variables}}), assistant (examples) Accepts: name, prompt (array of {role, content}), optional labels, config, tags, commitMessage
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 255,
"description": "The name of the prompt"
},
"prompt": {
"minItems": 1,
"type": "array",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string",
"description": "The role (e.g., 'system', 'user', 'assistant')"
},
"content": {
"type": "string",
"description": "The message content"
}
},
"required": [
"role",
"content"
],
"additionalProperties": false
},
"description": "Array of chat messages with role and content"
},
"labels": {
"description": "Labels to assign (e.g., ['production', 'staging'])",
"type": "array",
"items": {
"type": "string"
}
},
"config": {
"description": "Optional JSON config (e.g., {model: 'gpt-4', temperature: 0.7})",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"tags": {
"description": "Optional tags for organization (e.g., ['experimental', 'v2'])",
"type": "array",
"items": {
"type": "string"
}
},
"commitMessage": {
"description": "Optional commit message describing the changes",
"type": "string"
}
},
"required": [
"name",
"prompt"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createChatPrompt",
"arguments": {
"name": "string",
"prompt": [
{
"content": "string",
"role": "string"
}
],
"commitMessage": "string",
"config": {
"property": {}
},
"labels": [
"string"
],
"tags": [
"string"
]
}
}
}updatePromptLabels
Update labels for a specific prompt version. Important: - ONLY way to modify existing prompts (labels only) - Specified labels are added to the version (preserving others not mentioned) - Labels are unique across versions - setting a label on one version automatically removes it from others - 'latest' label is auto-managed and cannot be set manually - Cannot modify prompt content, type, or tags - use createTextPrompt or createChatPrompt for new versions Accepts: name, version (required), newLabels (array, can be empty to remove all labels)
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 255,
"description": "The name of the prompt"
},
"version": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991,
"description": "The version number to update (required)"
},
"newLabels": {
"type": "array",
"items": {
"type": "string"
},
"description": "Array of new labels to assign to the prompt version (can be empty to remove all labels). The 'latest' label is auto-managed and cannot be supplied."
}
},
"required": [
"name",
"version",
"newLabels"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "updatePromptLabels",
"arguments": {
"name": "string",
"newLabels": [
"string"
],
"version": 1
}
}
}listObservations
Find and review observations in the current Langfuse project, such as generations, spans, events, agent steps, and tool calls. Use filters to narrow results by trace, name, type, level, environment, time range, or advanced filter conditions. Results are paginated with an opaque cursor. By default this returns compact summary fields. Use fields: ["*"] for the full observation, or pass specific field names to limit the response size. Important: if you request metadata explicitly, for example fields: ["id", "metadata"], metadata values are truncated to 200 UTF-8 characters per key unless you also pass expandMetadataKeys with the keys that may need full values. Requests that project or filter input, output, or metadata must include traceId, an id filter, or both fromStartTime and toStartTime.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"fields": {
"description": "Observation fields to include in the response. Omit for compact defaults, use [\"*\"] for all available fields, or pass specific field names to keep responses small. Call getObservationFieldSchema to list accepted fields.",
"type": "array",
"items": {
"type": "string"
}
},
"expandMetadataKeys": {
"description": "Metadata keys that may need full values. Metadata values are truncated to 200 UTF-8 characters per key by default when metadata is projected without this option.",
"type": "array",
"items": {
"type": "string"
}
},
"limit": {
"default": 50,
"description": "Number of observations to return (1-100, default: 50)",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"cursor": {
"description": "Cursor returned by a previous listObservations call",
"type": "string"
},
"type": {
"type": "string",
"enum": [
"SPAN",
"EVENT",
"GENERATION",
"AGENT",
"TOOL",
"CHAIN",
"RETRIEVER",
"EVALUATOR",
"EMBEDDING",
"GUARDRAIL"
]
},
"name": {
"type": "string"
},
"userId": {
"type": "string"
},
"level": {
"type": "string",
"enum": [
"DEBUG",
"DEFAULT",
"WARNING",
"ERROR"
]
},
"traceId": {
"type": "string"
},
"version": {
"type": "string"
},
"parentObservationId": {
"type": "string"
},
"environment": {
"description": "Environment to filter by. Multiple environments are temporarily unsupported until the public observations API applies allow-multiple environment filters correctly.",
"type": "string"
},
"fromStartTime": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"toStartTime": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"filter": {
"description": "Advanced filters. Each item must be an object with column, operator, value, and optional type. Type is inferred from getObservationFilterSchema columns when omitted.",
"type": "array",
"items": {
"type": "object",
"properties": {
"column": {
"type": "string"
},
"operator": {
"type": "string"
},
"value": {},
"type": {
"type": "string"
}
},
"required": [
"column",
"operator",
"value"
],
"additionalProperties": false,
"description": "Advanced observation filter object. Example: {\"column\":\"totalCost\",\"operator\":\">\",\"value\":0.0029}. The explicit form {\"type\":\"number\",\"column\":\"totalCost\",\"operator\":\">\",\"value\":0.0029} is also accepted."
}
}
},
"required": [
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listObservations",
"arguments": {
"limit": 50,
"cursor": "string",
"environment": "string",
"expandMetadataKeys": [
"string"
],
"fields": [
"string"
],
"filter": [
{
"column": "string",
"operator": "string",
"value": {},
"type": "string"
}
],
"fromStartTime": "2026-05-15T12:00:00.000Z",
"level": "DEBUG",
"name": "string",
"parentObservationId": "string",
"toStartTime": "2026-05-15T12:00:00.000Z",
"traceId": "string",
"type": "SPAN",
"userId": "string",
"version": "string"
}
}
}getObservation
Get the details for a single observation in the current Langfuse project by observation ID. Use this when you already know the observation ID and want to inspect its timing, model, status, payload, metadata, usage, cost, or prompt fields. By default this returns compact summary fields. Use fields: ["*"] for the full observation, or pass specific field names to limit the response size. Important: if you request metadata explicitly, for example fields: ["id", "metadata"], metadata values are truncated to 200 UTF-8 characters per key unless you also pass expandMetadataKeys with the keys that may need full values.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"observationId": {
"type": "string",
"minLength": 1
},
"fields": {
"description": "Observation fields to include in the response. Omit for compact defaults, use [\"*\"] for all available fields, or pass specific field names to keep responses small. Call getObservationFieldSchema to list accepted fields.",
"type": "array",
"items": {
"type": "string"
}
},
"expandMetadataKeys": {
"description": "Metadata keys that may need full values. Metadata values are truncated to 200 UTF-8 characters per key by default when metadata is projected without this option.",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"observationId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getObservation",
"arguments": {
"observationId": "string",
"expandMetadataKeys": [
"string"
],
"fields": [
"string"
]
}
}
}getObservationFieldSchema
Show which observation fields can be requested from listObservations and getObservation. The response marks default fields and fields that may be large or contain sensitive application data.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {},
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getObservationFieldSchema",
"arguments": {}
}
}getObservationFilterSchema
Show which observation fields can be used in listObservations filters, including the supported operators for each field.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {},
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getObservationFilterSchema",
"arguments": {}
}
}getObservationFilterValues
List example values for a string or boolean observation filter field, such as names, types, levels, environments, model names, tags, users, or sessions. For numeric metric fields, returns a range with min, max, avg, and count. Use the returned cursor to page through long value lists.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"column": {
"type": "string",
"enum": [
"name",
"type",
"environment",
"version",
"userId",
"sessionId",
"traceName",
"level",
"promptName",
"promptVersion",
"modelId",
"providedModelName",
"totalCost",
"totalTokens",
"latency",
"timeToFirstToken",
"tags",
"hasParentObservation"
]
},
"fromStartTime": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"toStartTime": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"observationType": {
"type": "string",
"enum": [
"SPAN",
"EVENT",
"GENERATION",
"AGENT",
"TOOL",
"CHAIN",
"RETRIEVER",
"EVALUATOR",
"EMBEDDING",
"GUARDRAIL"
]
},
"hasParentObservation": {
"type": "boolean"
},
"limit": {
"default": 50,
"description": "Number of observations to return (1-100, default: 50)",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"cursor": {
"type": "string"
}
},
"required": [
"column",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getObservationFilterValues",
"arguments": {
"column": "name",
"limit": 50,
"cursor": "string",
"fromStartTime": "2026-05-15T12:00:00.000Z",
"hasParentObservation": true,
"observationType": "SPAN",
"toStartTime": "2026-05-15T12:00:00.000Z"
}
}
}listAnnotationQueues
List annotation queues, worklists that collect trace or observation items for human review and scoring, with pagination.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"page": {
"default": 1,
"type": "number",
"exclusiveMinimum": 0
},
"limit": {
"default": 50,
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listAnnotationQueues",
"arguments": {
"limit": 50,
"page": 1
}
}
}createAnnotationQueue
Create an annotation queue, a worklist that collects trace or observation items for human review and scoring.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"scoreConfigIds": {
"minItems": 1,
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"name",
"scoreConfigIds"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createAnnotationQueue",
"arguments": {
"name": "string",
"scoreConfigIds": [
"string"
],
"description": "string"
}
}
}getAnnotationQueue
Get an annotation queue, a worklist of trace or observation items for human review and scoring, by ID.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"queueId": {
"type": "string"
}
},
"required": [
"queueId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getAnnotationQueue",
"arguments": {
"queueId": "string"
}
}
}listAnnotationQueueItems
List annotation queue items, each linking one trace or observation to a queue with a review status, with optional status filtering.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"page": {
"default": 1,
"type": "number",
"exclusiveMinimum": 0
},
"limit": {
"default": 50,
"type": "number",
"minimum": 1,
"maximum": 100
},
"queueId": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"PENDING",
"COMPLETED"
]
}
},
"required": [
"page",
"limit",
"queueId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listAnnotationQueueItems",
"arguments": {
"limit": 50,
"page": 1,
"queueId": "string",
"status": "PENDING"
}
}
}getAnnotationQueueItem
Get an annotation queue item, one queued trace or observation with review status, by queue ID and item ID.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"queueId": {
"type": "string"
},
"itemId": {
"type": "string"
}
},
"required": [
"queueId",
"itemId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getAnnotationQueueItem",
"arguments": {
"itemId": "string",
"queueId": "string"
}
}
}createAnnotationQueueItem
Add an annotation queue item, one trace or observation to review, to a queue.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"queueId": {
"type": "string"
},
"objectId": {
"type": "string"
},
"objectType": {
"type": "string",
"enum": [
"TRACE",
"OBSERVATION",
"SESSION"
]
},
"status": {
"default": "PENDING",
"type": "string",
"enum": [
"PENDING",
"COMPLETED"
]
}
},
"required": [
"queueId",
"objectId",
"objectType",
"status"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createAnnotationQueueItem",
"arguments": {
"objectId": "string",
"objectType": "TRACE",
"queueId": "string",
"status": "PENDING"
}
}
}updateAnnotationQueueItem
Update an annotation queue item's review status, such as pending or completed.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"queueId": {
"type": "string"
},
"itemId": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"PENDING",
"COMPLETED"
]
}
},
"required": [
"queueId",
"itemId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "updateAnnotationQueueItem",
"arguments": {
"itemId": "string",
"queueId": "string",
"status": "PENDING"
}
}
}deleteAnnotationQueueItem
Remove an annotation queue item, the queued trace or observation, from a queue.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"queueId": {
"type": "string"
},
"itemId": {
"type": "string"
}
},
"required": [
"queueId",
"itemId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "deleteAnnotationQueueItem",
"arguments": {
"itemId": "string",
"queueId": "string"
}
}
}createAnnotationQueueAssignment
Assign a project user to an annotation queue so they can work through its review items.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"queueId": {
"type": "string"
},
"userId": {
"type": "string"
}
},
"required": [
"queueId",
"userId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createAnnotationQueueAssignment",
"arguments": {
"queueId": "string",
"userId": "string"
}
}
}deleteAnnotationQueueAssignment
Remove a project user's assignment from an annotation queue.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"queueId": {
"type": "string"
},
"userId": {
"type": "string"
}
},
"required": [
"queueId",
"userId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "deleteAnnotationQueueAssignment",
"arguments": {
"queueId": "string",
"userId": "string"
}
}
}createComment
Create a comment on a trace, observation, session, or prompt.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"content": {
"type": "string",
"minLength": 1,
"maxLength": 5000
},
"objectId": {
"type": "string"
},
"objectType": {
"type": "string",
"enum": [
"TRACE",
"OBSERVATION",
"SESSION",
"PROMPT"
]
},
"authorUserId": {
"type": "string"
}
},
"required": [
"content",
"objectId",
"objectType"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createComment",
"arguments": {
"content": "string",
"objectId": "string",
"objectType": "TRACE",
"authorUserId": "string"
}
}
}listComments
List comments in the current Langfuse project, optionally filtered by object or author.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"objectType": {
"type": "string",
"enum": [
"TRACE",
"OBSERVATION",
"SESSION",
"PROMPT"
]
},
"objectId": {
"type": "string"
},
"authorUserId": {
"type": "string"
},
"page": {
"default": 1,
"type": "number",
"exclusiveMinimum": 0
},
"limit": {
"default": 50,
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listComments",
"arguments": {
"limit": 50,
"page": 1,
"authorUserId": "string",
"objectId": "string",
"objectType": "TRACE"
}
}
}getComment
Get a comment by ID from the current Langfuse project.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"commentId": {
"type": "string"
}
},
"required": [
"commentId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getComment",
"arguments": {
"commentId": "string"
}
}
}upsertDataset
Upsert a dataset, a named collection of input and optional expected-output examples for experiments and evaluations.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1
},
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"metadata": {},
"inputSchema": {},
"expectedOutputSchema": {}
},
"required": [
"name"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "upsertDataset",
"arguments": {
"name": "string",
"description": "string",
"expectedOutputSchema": {},
"id": "string",
"inputSchema": {},
"metadata": {}
}
}
}listDatasets
List datasets, named collections of input and optional expected-output examples for experiments and evaluations. Optionally filter by dataset name to find a dataset ID.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string"
},
"page": {
"default": 1,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"limit": {
"default": 50,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listDatasets",
"arguments": {
"limit": 50,
"page": 1,
"name": "string"
}
}
}getDataset
Get a dataset, a named collection of input and optional expected-output examples for experiments and evaluations, by ID.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetId": {
"type": "string"
}
},
"required": [
"datasetId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getDataset",
"arguments": {
"datasetId": "string"
}
}
}upsertDatasetItem
Upsert a dataset item (one example in a dataset) by dataset ID
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetId": {
"type": "string"
},
"input": {},
"expectedOutput": {},
"metadata": {},
"id": {
"type": "string"
},
"sourceTraceId": {
"type": "string"
},
"sourceObservationId": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"ACTIVE",
"ARCHIVED"
]
}
},
"required": [
"datasetId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "upsertDatasetItem",
"arguments": {
"datasetId": "string",
"expectedOutput": {},
"id": "string",
"input": {},
"metadata": {},
"sourceObservationId": "string",
"sourceTraceId": "string",
"status": "ACTIVE"
}
}
}listDatasetItems
List dataset items, individual examples with input and optional expected output, optionally filtered by dataset ID, source trace, source observation, or version.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetId": {
"type": "string"
},
"sourceTraceId": {
"type": "string"
},
"sourceObservationId": {
"type": "string"
},
"version": {
"type": "string"
},
"page": {
"default": 1,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"limit": {
"default": 50,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listDatasetItems",
"arguments": {
"limit": 50,
"page": 1,
"datasetId": "string",
"sourceObservationId": "string",
"sourceTraceId": "string",
"version": "string"
}
}
}getDatasetItem
Get a dataset item, one example in a dataset with input and optional expected output, by ID.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetItemId": {
"type": "string"
}
},
"required": [
"datasetItemId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getDatasetItem",
"arguments": {
"datasetItemId": "string"
}
}
}deleteDatasetItem
Delete a dataset item, one example in a dataset, and all its run items.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetItemId": {
"type": "string"
}
},
"required": [
"datasetItemId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "deleteDatasetItem",
"arguments": {
"datasetItemId": "string"
}
}
}createDatasetRunItem
Create a dataset run item, a result that links one dataset item to a trace or observation in a dataset run.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"runName": {
"type": "string"
},
"runDescription": {
"type": "string"
},
"metadata": {},
"datasetItemId": {
"type": "string"
},
"observationId": {
"description": "Observation ID linked to this run item. Provide this or traceId.",
"type": "string"
},
"traceId": {
"description": "Trace ID linked to this run item. Provide this or observationId.",
"type": "string"
},
"datasetVersion": {
"type": "string"
},
"createdAt": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
}
},
"required": [
"runName",
"datasetItemId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createDatasetRunItem",
"arguments": {
"datasetItemId": "string",
"runName": "string",
"createdAt": "2026-05-15T12:00:00.000Z",
"datasetVersion": "string",
"metadata": {},
"observationId": "string",
"runDescription": "string",
"traceId": "string"
}
}
}listDatasetRunItems
List dataset run items, each linking one dataset item to a trace or observation within a dataset run, by dataset ID and run ID.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetId": {
"type": "string"
},
"datasetRunId": {
"type": "string"
},
"page": {
"default": 1,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"limit": {
"default": 50,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 100
}
},
"required": [
"datasetId",
"datasetRunId",
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listDatasetRunItems",
"arguments": {
"datasetId": "string",
"datasetRunId": "string",
"limit": 50,
"page": 1
}
}
}listDatasetRuns
List dataset runs, each experiment or evaluation execution over a dataset, by dataset ID.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetId": {
"type": "string"
},
"page": {
"default": 1,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"limit": {
"default": 50,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 100
}
},
"required": [
"datasetId",
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listDatasetRuns",
"arguments": {
"datasetId": "string",
"limit": 50,
"page": 1
}
}
}getDatasetRun
Get a dataset run, one experiment or evaluation execution over a dataset, and its run items by dataset ID and run ID.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetId": {
"type": "string"
},
"datasetRunId": {
"type": "string"
}
},
"required": [
"datasetId",
"datasetRunId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getDatasetRun",
"arguments": {
"datasetId": "string",
"datasetRunId": "string"
}
}
}deleteDatasetRun
Delete a dataset run by dataset ID and run ID, and enqueue deletion of its run items.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"datasetId": {
"type": "string"
},
"datasetRunId": {
"type": "string"
}
},
"required": [
"datasetId",
"datasetRunId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "deleteDatasetRun",
"arguments": {
"datasetId": "string",
"datasetRunId": "string"
}
}
}getHealth
Check Langfuse API health. Optionally verify database availability and recent trace/observation ingestion.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"failIfDatabaseUnavailable": {
"default": false,
"type": "boolean"
},
"failIfNoRecentEvents": {
"default": false,
"type": "boolean"
}
},
"required": [
"failIfDatabaseUnavailable",
"failIfNoRecentEvents"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getHealth",
"arguments": {
"failIfDatabaseUnavailable": false,
"failIfNoRecentEvents": false
}
}
}listScores
Find scores in Langfuse. Use this to review quality, evaluation, or feedback scores for traces, observations, sessions, and dataset runs. Filter by score details, time range, environment, source, trace information, or dataset run context to narrow the results. Score reads are eventually consistent: a score created with createScore may not appear in listScores immediately. If a newly created score is missing, wait briefly and retry.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"page": {
"default": 1,
"type": "number",
"exclusiveMinimum": 0
},
"limit": {
"default": 50,
"type": "number",
"minimum": 1,
"maximum": 100
},
"fields": {
"default": [
"score",
"trace"
],
"description": "Response field groups to include. 'score' is always required. Include 'trace' when filtering by userId or traceTags.",
"type": "array",
"items": {
"type": "string",
"enum": [
"score",
"trace"
]
}
},
"userId": {
"type": "string"
},
"dataType": {
"type": "string",
"enum": [
"NUMERIC",
"CATEGORICAL",
"BOOLEAN",
"CORRECTION",
"TEXT"
]
},
"configId": {
"type": "string"
},
"queueId": {
"type": "string"
},
"traceTags": {
"type": "array",
"items": {
"type": "string"
}
},
"environment": {
"type": "array",
"items": {
"type": "string"
}
},
"name": {
"type": "string"
},
"fromTimestamp": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"toTimestamp": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"source": {
"type": "string",
"enum": [
"API",
"EVAL",
"ANNOTATION"
]
},
"value": {
"type": "number"
},
"operator": {
"type": "string",
"enum": [
"<",
">",
"<=",
">=",
"!=",
"="
]
},
"scoreIds": {
"type": "array",
"items": {
"type": "string"
}
},
"sessionId": {
"type": "string"
},
"traceId": {
"type": "string"
},
"datasetRunId": {
"type": "string"
},
"observationId": {
"type": "array",
"items": {
"type": "string"
}
},
"filter": {
"description": "Advanced score filters as JSON objects with column, operator, value, and type.",
"type": "array",
"items": {
"type": "object",
"properties": {
"column": {
"type": "string"
},
"operator": {
"type": "string"
},
"value": {},
"type": {
"type": "string"
},
"key": {
"type": "string"
}
},
"required": [
"column",
"operator",
"value",
"type"
],
"additionalProperties": false
}
}
},
"required": [
"page",
"limit",
"fields"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listScores",
"arguments": {
"fields": [
"score",
"trace"
],
"limit": 50,
"page": 1,
"configId": "string",
"datasetRunId": "string",
"dataType": "NUMERIC",
"environment": [
"string"
],
"filter": [
{
"column": "string",
"operator": "string",
"type": "string",
"value": {},
"key": "string"
}
],
"fromTimestamp": "2026-05-15T12:00:00.000Z",
"name": "string",
"observationId": [
"string"
],
"operator": "<",
"queueId": "string",
"scoreIds": [
"string"
],
"sessionId": "string",
"source": "API",
"toTimestamp": "2026-05-15T12:00:00.000Z",
"traceId": "string",
"traceTags": [
"string"
],
"userId": "string",
"value": 1.23
}
}
}getScore
Fetch one score by ID from the current Langfuse project. Score reads are eventually consistent: a score created with createScore may not be returned by getScore immediately. If a newly created score is not found, wait briefly and retry.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"scoreId": {
"type": "string"
}
},
"required": [
"scoreId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getScore",
"arguments": {
"scoreId": "string"
}
}
}createScore
Create one score in the current Langfuse project. Score reads are eventually consistent: after creation, getScore and listScores may not return the new score immediately. Wait briefly and retry reads when confirming creation.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string",
"minLength": 1
},
"traceId": {
"description": "Target trace ID.",
"type": "string"
},
"sessionId": {
"description": "Target session ID.",
"type": "string"
},
"datasetRunId": {
"description": "Target dataset run ID.",
"type": "string"
},
"observationId": {
"description": "Optional observation ID for trace-scoped scores.",
"type": "string"
},
"comment": {
"type": "string"
},
"metadata": {},
"environment": {
"type": "string"
},
"queueId": {
"type": "string"
},
"source": {
"type": "string",
"enum": [
"API",
"ANNOTATION"
]
},
"value": {
"description": "Score value. Must be a JSON number for NUMERIC and BOOLEAN scores; numeric strings like \"0.92\" are invalid. Use a string for CATEGORICAL, TEXT, and CORRECTION scores."
},
"dataType": {
"description": "Score data type. When omitted, legacy scoring accepts string or number values.",
"type": "string",
"enum": [
"NUMERIC",
"CATEGORICAL",
"BOOLEAN",
"CORRECTION",
"TEXT"
]
},
"configId": {
"type": "string"
}
},
"required": [
"name",
"value"
],
"additionalProperties": false,
"description": "Create score request. Provide exactly one of traceId, sessionId, or datasetRunId. observationId may only be provided together with traceId."
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createScore",
"arguments": {
"name": "string",
"value": {},
"comment": "string",
"configId": "string",
"datasetRunId": "string",
"dataType": "NUMERIC",
"environment": "string",
"id": "string",
"metadata": {},
"observationId": "string",
"queueId": "string",
"sessionId": "string",
"source": "API",
"traceId": "string"
}
}
}listScoreConfigs
List score configurations. Returns exactly data and meta at the top level.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"page": {
"default": 1,
"type": "number",
"exclusiveMinimum": 0
},
"limit": {
"default": 50,
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listScoreConfigs",
"arguments": {
"limit": 50,
"page": 1
}
}
}getScoreConfig
Fetch one score configuration by ID from the current Langfuse project. Returns the public score config object directly.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"configId": {
"type": "string"
}
},
"required": [
"configId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getScoreConfig",
"arguments": {
"configId": "string"
}
}
}createScoreConfig
Create a score configuration. Supports numeric, categorical, boolean, and text configs. Boolean configs automatically receive True and False categories.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 35,
"pattern": "^[\\p{L}\\p{N}_ .()-]+$",
"description": "Allowed characters: letters, numbers, spaces, underscores, periods, parentheses, and hyphens."
},
"description": {
"type": "string"
},
"dataType": {
"type": "string",
"enum": [
"NUMERIC",
"CATEGORICAL",
"BOOLEAN",
"TEXT"
],
"description": "Score config type. Numeric range fields only apply to NUMERIC configs; categorical categories only apply to CATEGORICAL configs."
},
"numericMinValue": {
"description": "Minimum allowed value for NUMERIC score configs.",
"type": "number"
},
"numericMaxValue": {
"description": "Maximum allowed value for NUMERIC score configs.",
"type": "number"
},
"categoricalCategories": {
"description": "Allowed categories for CATEGORICAL score configs as an array of { label, value } objects."
}
},
"required": [
"name",
"dataType"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createScoreConfig",
"arguments": {
"dataType": "NUMERIC",
"name": "string",
"categoricalCategories": {},
"description": "string",
"numericMaxValue": 1.23,
"numericMinValue": 1.23
}
}
}updateScoreConfig
Update a score configuration. Use this to rename, describe, or adjust allowed numeric/category fields.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"configId": {
"type": "string"
},
"name": {
"type": "string",
"minLength": 1,
"maxLength": 35,
"pattern": "^[\\p{L}\\p{N}_ .()-]+$",
"description": "Allowed characters: letters, numbers, spaces, underscores, periods, parentheses, and hyphens."
},
"numericMinValue": {
"description": "Minimum allowed value for NUMERIC score configs.",
"type": "number"
},
"numericMaxValue": {
"description": "Maximum allowed value for NUMERIC score configs.",
"type": "number"
},
"categoricalCategories": {
"description": "Allowed categories for CATEGORICAL score configs as an array of { label, value } objects."
},
"description": {
"type": "string"
}
},
"required": [
"configId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "updateScoreConfig",
"arguments": {
"configId": "string",
"categoricalCategories": {},
"description": "string",
"name": "string",
"numericMaxValue": 1.23,
"numericMinValue": 1.23
}
}
}deleteScoreConfig
Delete a score configuration from the current Langfuse project by archiving it.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"configId": {
"type": "string"
}
},
"required": [
"configId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "deleteScoreConfig",
"arguments": {
"configId": "string"
}
}
}queryMetrics
Answer analytics questions about the current Langfuse project, such as usage over time, model costs, latency, errors, scores, or grouped breakdowns by environment, trace, observation, model, user, session, tag, or score name.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"view": {
"type": "string",
"enum": [
"observations",
"scores-numeric",
"scores-categorical"
]
},
"dimensions": {
"default": [],
"type": "array",
"items": {
"type": "object",
"properties": {
"field": {
"type": "string"
}
},
"required": [
"field"
],
"additionalProperties": false
}
},
"metrics": {
"type": "array",
"items": {
"type": "object",
"properties": {
"measure": {
"type": "string"
},
"aggregation": {
"type": "string",
"enum": [
"sum",
"avg",
"count",
"max",
"min",
"p50",
"p75",
"p90",
"p95",
"p99",
"histogram",
"uniq"
]
}
},
"required": [
"measure",
"aggregation"
],
"additionalProperties": false
}
},
"filters": {
"default": [],
"type": "array",
"items": {
"type": "object",
"properties": {
"column": {
"type": "string"
},
"operator": {
"type": "string"
},
"value": {},
"type": {
"type": "string"
},
"key": {
"type": "string"
}
},
"required": [
"column",
"operator",
"value",
"type"
],
"additionalProperties": false
}
},
"timeDimension": {
"type": "object",
"properties": {
"granularity": {
"type": "string",
"enum": [
"auto",
"minute",
"hour",
"day",
"week",
"month"
]
}
},
"required": [
"granularity"
],
"additionalProperties": false
},
"fromTimestamp": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"toTimestamp": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
},
"orderBy": {
"type": "array",
"items": {
"type": "object",
"properties": {
"field": {
"type": "string"
},
"direction": {
"type": "string",
"enum": [
"asc",
"desc"
]
}
},
"required": [
"field",
"direction"
],
"additionalProperties": false
}
},
"config": {
"type": "object",
"properties": {
"bins": {
"type": "integer",
"minimum": 1,
"maximum": 100
},
"row_limit": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 1000
}
},
"additionalProperties": false
}
},
"required": [
"view",
"dimensions",
"metrics",
"filters",
"fromTimestamp",
"toTimestamp"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "queryMetrics",
"arguments": {
"dimensions": [],
"filters": [],
"fromTimestamp": "2026-05-15T12:00:00.000Z",
"metrics": [
{
"aggregation": "sum",
"measure": "string"
}
],
"toTimestamp": "2026-05-15T12:00:00.000Z",
"view": "observations",
"config": {
"bins": 1,
"row_limit": 1
},
"orderBy": [
{
"direction": "asc",
"field": "string"
}
],
"timeDimension": {
"granularity": "auto"
}
}
}
}getMetricsSchema
Discover which Langfuse metrics can be analyzed and how to group, filter, aggregate, and time-bucket them before calling queryMetrics.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"view": {
"description": "Limit the response to one v2 metrics view",
"type": "string",
"enum": [
"observations",
"scores-numeric",
"scores-categorical"
]
}
},
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getMetricsSchema",
"arguments": {
"view": "observations"
}
}
}listModels
List custom and Langfuse-managed model definitions visible to the current project.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"page": {
"default": 1,
"type": "number",
"exclusiveMinimum": 0
},
"limit": {
"default": 50,
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listModels",
"arguments": {
"limit": 50,
"page": 1
}
}
}createModel
Create a custom model definition for cost tracking/tokenization in the current project.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"modelName": {
"type": "string"
},
"matchPattern": {
"type": "string"
},
"startDate": {
"type": "string"
},
"inputPrice": {
"type": "number",
"minimum": 0
},
"outputPrice": {
"type": "number",
"minimum": 0
},
"totalPrice": {
"type": "number",
"minimum": 0
},
"unit": {
"type": "string",
"enum": [
"TOKENS",
"CHARACTERS",
"MILLISECONDS",
"SECONDS",
"REQUESTS",
"IMAGES"
]
},
"tokenizerId": {
"type": "string",
"enum": [
"openai",
"claude"
]
},
"tokenizerConfig": {},
"pricingTiers": {
"type": "array",
"items": {}
}
},
"required": [
"modelName",
"matchPattern",
"unit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createModel",
"arguments": {
"matchPattern": "string",
"modelName": "string",
"unit": "TOKENS",
"inputPrice": 1.23,
"outputPrice": 1.23,
"pricingTiers": [
{}
],
"startDate": "string",
"tokenizerConfig": {},
"tokenizerId": "openai",
"totalPrice": 1.23
}
}
}getModel
Get a model definition by ID from the current project scope.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"modelId": {
"type": "string"
}
},
"required": [
"modelId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getModel",
"arguments": {
"modelId": "string"
}
}
}deleteModel
Delete a custom model definition from the current project. Built-in models cannot be deleted.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"modelId": {
"type": "string"
}
},
"required": [
"modelId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "deleteModel",
"arguments": {
"modelId": "string"
}
}
}getMedia
Fetch metadata and a signed download URL for one media asset.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"mediaId": {
"type": "string"
}
},
"required": [
"mediaId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getMedia",
"arguments": {
"mediaId": "string"
}
}
}listEvaluators
List evaluators (llm_as_judge and code) defined in the current Langfuse project. Results are paginated.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"page": {
"default": 1,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"limit": {
"default": 50,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listEvaluators",
"arguments": {
"limit": 50,
"page": 1
}
}
}getEvaluator
Fetch a single evaluator by id, including its prompt or source code, output definition, and how many evaluation rules reference it.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"evaluatorId": {
"type": "string"
}
},
"required": [
"evaluatorId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getEvaluator",
"arguments": {
"evaluatorId": "string"
}
}
}upsertEvaluator
Create an evaluator, or add a new version to an existing one in the current project. Set type to `llm_as_judge` (default) and provide prompt + outputDefinition (modelConfig optional), or set type to `code` and provide sourceCode + sourceCodeLanguage. Reusing an existing evaluator name adds a new version and migrates evaluation rules that reference it.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1
},
"type": {
"description": "Evaluator type. Defaults to `llm_as_judge` when omitted.",
"type": "string",
"enum": [
"llm_as_judge",
"code"
]
},
"prompt": {
"type": "string",
"minLength": 1
},
"outputDefinition": {
"type": "object",
"properties": {
"dataType": {
"type": "string",
"enum": [
"NUMERIC",
"BOOLEAN",
"CATEGORICAL"
]
},
"reasoning": {
"type": "object",
"properties": {
"description": {
"type": "string",
"minLength": 1
}
},
"required": [
"description"
],
"additionalProperties": false
},
"score": {
"type": "object",
"properties": {
"description": {
"type": "string",
"minLength": 1
},
"categories": {
"minItems": 2,
"type": "array",
"items": {
"type": "string",
"minLength": 1
}
},
"shouldAllowMultipleMatches": {
"type": "boolean"
}
},
"required": [
"description"
],
"additionalProperties": false
}
},
"required": [
"dataType",
"reasoning",
"score"
],
"additionalProperties": false,
"description": "Score output definition. Required when type is `llm_as_judge`; omit for `code` evaluators."
},
"modelConfig": {
"type": "object",
"properties": {
"provider": {
"type": "string",
"minLength": 1
},
"model": {
"type": "string",
"minLength": 1
}
},
"required": [
"provider",
"model"
],
"additionalProperties": false,
"description": "Model used for `llm_as_judge` evaluation. Optional; falls back to the project default eval model."
},
"sourceCode": {
"type": "string",
"minLength": 1
},
"sourceCodeLanguage": {
"type": "string",
"enum": [
"PYTHON",
"TYPESCRIPT"
]
}
},
"required": [
"name"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "upsertEvaluator",
"arguments": {
"name": "string",
"modelConfig": {
"model": "string",
"provider": "string"
},
"outputDefinition": {
"dataType": "NUMERIC",
"reasoning": {
"description": "string"
},
"score": {
"description": "string",
"categories": [
"string"
],
"shouldAllowMultipleMatches": true
}
},
"prompt": "string",
"sourceCode": "string",
"sourceCodeLanguage": "PYTHON",
"type": "llm_as_judge"
}
}
}listEvaluationRules
List evaluation rules in the current Langfuse project. Each rule attaches an evaluator to incoming observations or experiment items. Results are paginated.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"page": {
"default": 1,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"limit": {
"default": 50,
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 100
}
},
"required": [
"page",
"limit"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "listEvaluationRules",
"arguments": {
"limit": 50,
"page": 1
}
}
}getEvaluationRule
Fetch a single evaluation rule by id, including its evaluator reference, target, filter, variable mapping, sampling, and status.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"evaluationRuleId": {
"type": "string"
}
},
"required": [
"evaluationRuleId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getEvaluationRule",
"arguments": {
"evaluationRuleId": "string"
}
}
}createEvaluationRule
Create an evaluation rule that runs an evaluator on new observations or experiment items. Set target to `observation` or `experiment`. For `llm_as_judge` evaluators provide a variable mapping; for `code` evaluators omit mapping (Langfuse manages it).
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1
},
"evaluator": {
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1
},
"scope": {
"type": "string",
"enum": [
"project",
"managed"
]
},
"type": {
"default": "llm_as_judge",
"type": "string",
"enum": [
"llm_as_judge",
"code"
]
}
},
"required": [
"name",
"scope",
"type"
],
"additionalProperties": false
},
"enabled": {
"type": "boolean"
},
"sampling": {
"default": 1,
"type": "number",
"exclusiveMinimum": 0,
"maximum": 1
},
"target": {
"type": "string",
"enum": [
"observation",
"experiment"
]
},
"filter": {
"description": "Conditions selecting which items the rule runs on.",
"type": "array",
"items": {
"type": "object",
"properties": {
"column": {
"type": "string"
},
"operator": {
"type": "string"
},
"value": {},
"type": {
"type": "string"
},
"key": {
"type": "string"
}
},
"required": [
"column",
"operator",
"value",
"type"
],
"additionalProperties": false,
"description": "Filter condition, e.g. {\"column\":\"version\",\"operator\":\"=\",\"value\":\"1.0.0\",\"type\":\"string\"}. Use `key` for object columns such as `metadata`. `observation` rules filter on trace/observation columns; `experiment` rules filter on `datasetId`."
}
},
"mapping": {
"description": "Variable mapping. Required for `llm_as_judge` evaluators; omit for `code` evaluators.",
"type": "array",
"items": {
"type": "object",
"properties": {
"variable": {
"type": "string",
"minLength": 1
},
"source": {
"type": "string",
"enum": [
"input",
"output",
"metadata",
"expected_output",
"experiment_item_metadata"
]
},
"jsonPath": {
"type": "string",
"minLength": 1
}
},
"required": [
"variable",
"source"
],
"additionalProperties": false,
"description": "Maps an evaluator variable to a data source. `observation` rules use `input`, `output`, `metadata`; `experiment` rules also allow `expected_output` and `experiment_item_metadata`. Required for `llm_as_judge` evaluators; omit for `code` evaluators (Langfuse manages their mapping)."
}
}
},
"required": [
"name",
"evaluator",
"enabled",
"sampling",
"target"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "createEvaluationRule",
"arguments": {
"enabled": true,
"evaluator": {
"name": "string",
"scope": "project",
"type": "llm_as_judge"
},
"name": "string",
"sampling": 1,
"target": "observation",
"filter": [
{
"column": "string",
"operator": "string",
"type": "string",
"value": {},
"key": "string"
}
],
"mapping": [
{
"source": "input",
"variable": "string",
"jsonPath": "string"
}
]
}
}
}updateEvaluationRule
Update an existing evaluation rule. Provide evaluationRuleId plus at least one field to change. When updating filter or mapping, also pass the matching target. The evaluator type cannot be changed.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"evaluationRuleId": {
"type": "string"
},
"name": {
"type": "string",
"minLength": 1
},
"evaluator": {
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1
},
"scope": {
"type": "string",
"enum": [
"project",
"managed"
]
}
},
"required": [
"name",
"scope"
],
"additionalProperties": false
},
"enabled": {
"type": "boolean"
},
"sampling": {
"type": "number",
"exclusiveMinimum": 0,
"maximum": 1
},
"target": {
"description": "Provide together with filter/mapping when changing them; must match the rule's target.",
"type": "string",
"enum": [
"observation",
"experiment"
]
},
"filter": {
"type": "array",
"items": {
"type": "object",
"properties": {
"column": {
"type": "string"
},
"operator": {
"type": "string"
},
"value": {},
"type": {
"type": "string"
},
"key": {
"type": "string"
}
},
"required": [
"column",
"operator",
"value",
"type"
],
"additionalProperties": false,
"description": "Filter condition, e.g. {\"column\":\"version\",\"operator\":\"=\",\"value\":\"1.0.0\",\"type\":\"string\"}. Use `key` for object columns such as `metadata`. `observation` rules filter on trace/observation columns; `experiment` rules filter on `datasetId`."
}
},
"mapping": {
"type": "array",
"items": {
"type": "object",
"properties": {
"variable": {
"type": "string",
"minLength": 1
},
"source": {
"type": "string",
"enum": [
"input",
"output",
"metadata",
"expected_output",
"experiment_item_metadata"
]
},
"jsonPath": {
"type": "string",
"minLength": 1
}
},
"required": [
"variable",
"source"
],
"additionalProperties": false,
"description": "Maps an evaluator variable to a data source. `observation` rules use `input`, `output`, `metadata`; `experiment` rules also allow `expected_output` and `experiment_item_metadata`. Required for `llm_as_judge` evaluators; omit for `code` evaluators (Langfuse manages their mapping)."
}
}
},
"required": [
"evaluationRuleId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "updateEvaluationRule",
"arguments": {
"evaluationRuleId": "string",
"enabled": true,
"evaluator": {
"name": "string",
"scope": "project"
},
"filter": [
{
"column": "string",
"operator": "string",
"type": "string",
"value": {},
"key": "string"
}
],
"mapping": [
{
"source": "input",
"variable": "string",
"jsonPath": "string"
}
],
"name": "string",
"sampling": 1.23,
"target": "observation"
}
}
}deleteEvaluationRule
Delete an evaluation rule by id. This stops the rule from evaluating new items and cannot be undone.
Input schema and generated requestExpandCollapse
Input schema
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"evaluationRuleId": {
"type": "string"
}
},
"required": [
"evaluationRuleId"
],
"additionalProperties": false
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "deleteEvaluationRule",
"arguments": {
"evaluationRuleId": "string"
}
}
}Langfuse Docs MCP
Unauthenticated MCP server for Langfuse documentation search and retrieval.
https://langfuse.com/api/mcpClient setup
Cursor mcp.json
json
{
"mcpServers": {
"langfuse-docs": {
"url": "https://langfuse.com/api/mcp"
}
}
}Tools
searchLangfuseDocs
Semantic search (RAG) over the Langfuse documentation. Use this whenever the user asks a broader question that cannot be answered by a specific single page. Returns a concise answer synthesized from relevant docs. The raw provider response is included in _meta. Prefer this before guessing. If a specific page is needed call getLangfuseDocsPage first.
Input schema and generated requestExpandCollapse
Input schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The user's question in natural language. Include helpful context like SDK/language (e.g., Python v3, JS v4), self-hosted vs cloud, and short error messages (trim long stack traces). Keep under ~600 characters."
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "searchLangfuseDocs",
"arguments": {
"query": "string"
}
}
}getLangfuseDocsPage
Fetch the raw Markdown for a single Langfuse docs page. Accepts a docs path (e.g., /docs/observability/overview) or a full https://langfuse.com URL. Returns the exact Markdown (may include front matter). Use when you need a specific page content (Integration, Features, API, etc.) or code samples. Prefer searchLangfuseDocs for broader questions where there is not one specific page about it.
Input schema and generated requestExpandCollapse
Input schema
{
"type": "object",
"properties": {
"pathOrUrl": {
"type": "string",
"description": "Docs path starting with \"/\" (e.g., /docs/observability/overview) or a full URL on https://langfuse.com. Do not include anchors (#...) or queries (?foo=bar) — they will be ignored."
}
},
"required": [
"pathOrUrl"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getLangfuseDocsPage",
"arguments": {
"pathOrUrl": "string"
}
}
}getLangfuseOverview
Get a high-level, machine-readable index by downloading https://langfuse.com/llms.txt. Use this at the start of a session when needed to discover key docs endpoints or to seed follow-up calls to searchLangfuseDocs or getLangfuseDocsPage. Returns the plain text contents of llms.txt. Avoid repeated calls within the same session.
Input schema and generated requestExpandCollapse
Input schema
{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Generated request
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "getLangfuseOverview",
"arguments": {}
}
}