# Langfuse

SecureOfficial RemoteData, Analytics & Code Quality

**Summary:** Official Langfuse MCP server for prompt management, prompt discovery, and prompt label operations.

**How Teams Use It:** The Barndoor Langfuse MCP Server enables agents to query and manage prompts, scores, and observations, and analyze LLM usage metrics and costs, making it secure and efficient for AI evaluation and quality monitoring workflows.

## Tools

| Tool Name                         | Tool Description                                                                 | Tool Type |
|-----------------------------------|----------------------------------------------------------------------------------|-----------|
| createAnnotationQueue             | Create an annotation queue, a worklist that collects items for human review and scoring. | Create    |
| createAnnotationQueueAssignment    | Assign a project user to an annotation queue for review work.                   | Create    |
| createAnnotationQueueItem          | Add a trace or observation to an annotation queue for review.                   | Create    |
| createChatPrompt                  | Create a new chat prompt version in Langfuse.                                  | Create    |
| createComment                      | Create a comment on a trace, observation, session, or prompt.                  | Create    |
| createDatasetRunItem              | Create a dataset run item that links one dataset item to a trace or observation in a run. | Create    |
| createModel                        | Create a custom model definition for cost tracking and tokenization in the current project. | Create    |
| createScore                        | Create one score in the current Langfuse project.                              | Create    |
| createScoreConfig                 | Create a score configuration.                                                   | Create    |
| createTextPrompt                  | Create a new text prompt version in Langfuse.                                  | Create    |
| deleteAnnotationQueueAssignment     | Remove a project user's assignment from an annotation queue.                    | Delete    |
| deleteAnnotationQueueItem         | Remove a queued trace or observation from an annotation queue.                  | Delete    |
| deleteDatasetItem                 | Delete a dataset item and all its run items.                                   | Delete    |
| deleteDatasetRun                  | Delete a dataset run by dataset ID and run ID and enqueue deletion of its run items. | Delete    |
| deleteModel                        | Delete a custom model definition from the current project.                      | Delete    |
| deleteScoreConfig                 | Delete a score configuration from the current Langfuse project by archiving it. | Delete    |
| getAnnotationQueue                | Get an annotation queue, a worklist of items for human review and scoring, by ID. | Read      |
| getAnnotationQueueItem            | Get an annotation queue item with review status by queue ID and item ID.       | Read      |
| getComment                         | Get a comment by ID from the current Langfuse project.                        | Read      |
| getDataset                        | Get a dataset by ID, a named collection of examples for experiments and evaluations. | Read      |