mcpField
L
langfuse

langfuse

github.com/avivsinaiTesting & quality112129 installsUpdated 2d ago
Repository

About langfuse

A Langfuse investigation skill for tracing symptoms to relevant traces, observations, sessions, prompts, or datasets. It emphasizes reproducible, read-only diagnosis and clear boundaries around changes and sensitive trace data.

Key features

  1. 01Trace and exception discovery
  2. 02Inspect trace inputs and outputs
  3. 03Read-only diagnostic workflow
  4. 04Guidance on mutation and credentials

Use cases

  1. 01Find traces linked to a recent symptom
  2. 02Inspect latency, errors, or session behavior
  3. 03Keep diagnosis read-only unless changes are requested

MCP support

Provides guidance for using Langfuse MCP tools, including read-only server mode and setup, query, and output considerations.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/avivsinai/langfuse-mcp --skill langfuse

After installing, type/langfusein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
setup.md
tool-reference.md
workflows.md

Details

From the project README

Langfuse

Use Langfuse evidence to move from a broad symptom to the relevant trace, observation, session, prompt, or dataset. Start with the narrowest read-only query that can locate the event, then inspect its concrete inputs, outputs, timing, and errors.

Route the task

  • For trace, observation, exception, latency, or session diagnosis, read diagnostic and management workflows.
  • For installation, credentials, tool groups, output defaults, connection failures, or empty results, read setup.
  • For exact parameters, filters, pagination, output modes, and response shapes, read the tool reference.

A common investigation starts with fetch_traces(age=60) or find_exceptions(age=1440, group_by="file"), then fetches the selected trace or observation by ID. Use full_json_file only when the complete payload is needed; exports can contain sensitive user data.

Evidence and mutation boundaries

  • Treat model names, prompts, timestamps, and other values in historical traces as recorded evidence. Do not rewrite or normalize old model identifiers to a current name such as gpt-6-astra.

  • Trace discovery and inspection are read-only. Prompt creation or relabeling, dataset changes, annotation-queue changes, and deletions mutate Langfuse; perform them only when the user requested that change.

  • Prefer read-only server mode for diagnostic work. It disables prompt and dataset write tools:

    langfuse-mcp --read-only
# or LANGFUSE_MCP_READ_ONLY=true

  • Never commit Langfuse credentials. Keep public key, secret key, and host in the supported environment or MCP configuration described in the setup reference. Rotate any exposed key.

  • Preserve exact IDs and filters in findings so another reader can reproduce the query. State when pagination, lookback limits, or compact output limits the conclusion.

Comments

Markdown supported