Skip to main content
Glama
mgcrea

mcp-langfuse

by mgcrea
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Related Servers

Alternatives to mcp-langfuse

No user-submitted related servers found.

    Related Servers

    • langfuse-mcp

      avivsinai
      A
      license
      C
      quality
      A
      maintenance
      MCP server for Langfuse observability. Query traces, debug exceptions, analyze sessions, and manage prompts and datasets for your LLM applications.
      48
      3,600 PyPI
      112
      MIT

    • langfuse-mcp

      verma855
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents and MCP clients to query Langfuse observability data locally, covering traces, observations, sessions, exceptions, route decisions, prompts, datasets, annotation queues, scores, and aggregated metrics. Supports selective tool-group loading and a read-only mode for safer debugging and triage workflows.
      -

    • Langfuse MCP Server

      pablokrylov766
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents and developers to query traces, observations, sessions, and exceptions, plus prompts, datasets, annotation queues, scores, and aggregated metrics, for local debugging and observability from any MCP client. Supports selective tool-group loading to cut token overhead and a read-only mode that disables all write operations.
      -

    • Langfuse MCP Server

      Catherineh0509
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents and developers to query Langfuse telemetry locally, fetching traces, sessions, observations, and exceptions, inspecting route decisions, and running metrics, prompt, dataset, and annotation-queue operations. Supports selective tool-group loading and a read-only mode for token-efficient debugging from Claude Code, Codex, Cursor, or any MCP client.
      -
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.1/5.0

    Scored across 1 tool

    Disambiguation4/5

    With only one tool exposed there is no possible confusion between tools, so selection is unambiguous. However, the description repeatedly refers to "the other tools' `project` argument," which do not exist in this set, so an agent may waste effort looking for tools that aren't there.

    Naming Consistency4/5

    The single name `langfuse_auth_status` is clear, prefixed, and uses consistent snake_case. There is no multi-tool set to verify a pattern against, so consistency can only be judged on readability.

    Tool Count2/5

    A Langfuse observability server exposing exactly one diagnostic/status tool is far too thin for the apparent scope (projects, traces, sessions, scores). The description itself implies a larger intended surface, making this a notable under-scoping rather than a deliberately minimal server.

    Completeness1/5

    There are no tools to actually read Langfuse data — no trace, session, observation, score, or project listing operations — despite the tool describing itself as the entry point to a broader set. An agent can check auth status and then hit a dead end for every real workflow.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources