Langfuse

com.pulsemcpPublished by pulsemcp.comv0.1.3Updated Nov 3, 2026

MCP server for Langfuse LLM observability — trace and observation analysis.

VerifiedSTDIODesktop onlySecurity & MonitoringAI & ML

Overview

AI-generated overview

Read-only MCP server for inspecting Langfuse LLM traces and observations, letting an assistant browse, filter and drill into trace data, costs and latency.

What you can do
  • List and filter traces by name, user, session, tags, timestamps and environment, with pagination and minimal summaries
  • Fetch a full trace by ID, including nested observations, scores, input/output and metadata
  • List observations filtered by trace ID, type (GENERATION, SPAN, EVENT), model or level
  • Fetch a single observation with input, output, model parameters, usage and cost details
  • Read a server config/status resource for debugging
  • Offload oversized payloads: strings over 1000 characters are truncated and the full content saved to a temp file whose path is returned for grep-style searching
When to use it
Useful when you already run Langfuse and want an assistant to debug LLM pipelines, inspect prompts and completions, or analyze token usage, cost and latency without leaving the chat. It is read-only, so it suits investigation rather than changing anything in Langfuse.
Requirements
Runs locally via npx (Node.js) as a stdio process, configured in the desktop client. Requires a Langfuse public key (LANGFUSE_PUBLIC_KEY) and secret key (LANGFUSE_SECRET_KEY); LANGFUSE_BASE_URL is optional and defaults to the Langfuse cloud endpoint. Network access to the Langfuse API is needed.
Before you install
Requires Langfuse API credentials (LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY) stored in the client config; treat them as secrets. Trace data, including prompts and completions, is sent to the assistant and large payloads are written to temp files on the local machine, so sensitive content may be exposed. The server is described as read-only, with no write operations.

Installation

In SourceWeft

  1. Open Langfuse in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Langfuse MCP Server

MCP server for readonly analysis of Langfuse LLM traces and observations. Designed to help agents deeply inspect trace data, debug LLM pipelines, and analyze costs and latency.

Highlights

  • Browse and filter traces by name, user, session, tags, timestamps, and environment
  • Drill into full trace details including all nested observations and scores
  • List and filter observations by type (GENERATION, SPAN, EVENT), model, level, and more
  • Automatic truncation of large payloads (>1000 chars) to /tmp files with grep-friendly references
  • Read-only — no write operations, safe to use without risk of data modification

Capabilities

Tools

ToolDescription
get_tracesList traces with filtering and pagination. Returns minimal summary (no I/O fields).
get_trace_detailGet full trace by ID including observations, scores, input/output, and metadata.
get_observationsList observations with filtering by traceId, type, level, etc. Returns minimal summary.
get_observationGet full observation by ID including input, output, model parameters, usage, and cost details.

Resources

ResourceDescription
langfuse://configServer configuration and status (for debugging)

Large Payload Handling

Trace and observation data often contains very large input/output fields (full prompts, completions, etc.). This server automatically:

  1. Truncates any string field longer than 1000 characters
  2. Saves the full content to a /tmp/langfuse_*.txt file
  3. Includes the file path in the truncated output

Agents can then use grep to search within these files for specific content without loading the entire payload into context.

Configuration

Environment Variables

VariableRequiredDescriptionDefault
LANGFUSE_SECRET_KEYYesLangfuse secret key (sk-lf-...)-
LANGFUSE_PUBLIC_KEYYesLangfuse public key (pk-lf-...)-
LANGFUSE_BASE_URLNoLangfuse API base URLhttps://cloud.langfuse.com

Claude Desktop Configuration

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

json
{  "mcpServers": {    "langfuse": {      "command": "npx",      "args": ["-y", "langfuse-observability-mcp-server"],      "env": {        "LANGFUSE_SECRET_KEY": "sk-lf-your-secret-key",        "LANGFUSE_PUBLIC_KEY": "pk-lf-your-public-key",        "LANGFUSE_BASE_URL": "https://us.cloud.langfuse.com"      }    }  }}

Development

bash
# Install dependenciesnpm run install-all
# Buildnpm run build
# Development modenpm run dev
# Run functional testsnpm test
# Run integration testsnpm run test:integration
# Run manual tests (requires .env with real credentials)npm run test:manual

License

MIT

Source: experimental/langfuse/README.md at commit 0ed34de

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts