LangfuseCAUTION
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://badge.fury.io/py/langfuse-mcp) [](https://github.com/avivsinai/langfuse-mcp/stargazers) [](https://pypistats.org/packages/langfuse-mcp) [](https://pepy.tech/projects/langfuse-mcp) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT)
Usage: 12,518 PyPI downloads last month (pypistats, 2026-08-19). v0.10.1.
Local MCP server and skill for Langfuse. Debug traces, sessions, and exceptions from Claude Code, Codex, Cursor, or any MCP client.
Why this instead of native Langfuse MCP?
Use this for local debug: first-class traces, sessions, and exceptions; route-decision tools; compact / file-dump output; plus the included langfuse skill.
Use official Langfuse MCP for hosted, zero-install access to the broader API (score writes, comments, models, media).
As of June 2026:
1fb851f74378OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add langfuse-mcp --env LANGFUSE_PUBLIC_KEY=${LANGFUSE_PUBLIC_KEY} --env LANGFUSE_SECRET_KEY=${LANGFUSE_SECRET_KEY} -- uvx langfuse-mcp==0.12.1Trust audit
CAUTIONgrade B · trust 82/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- found
Findings (13)
.agents/skills/langfuse
.claude/skills/langfuse
mod = importlib.import_module(path)
LANGFUSE_HOST="http://127.0.0.1:9" \
secret = "super-secret-value-abc123"
.gitleaks.toml
.gitleaksignore
.pre-commit-config.yaml
@test "$$(readlink .claude/skills/langfuse)" = "../../skills/langfuse" || (echo "❌ .claude/skills/langfuse target is not ../../skills/langfuse" && exit 1)
@test "$$(readlink .agents/skills/langfuse)" = "../../skills/langfuse" || (echo "❌ .agents/skills/langfuse target is not ../../skills/langfuse" && exit 1)
decoded = base64.b64decode(credentials.strip().encode()).decode("utf-8")curl -sSf https://astral.sh/uv/install.sh | bash
Gates applied: no_behavioural_pass.
1fb851f74378full audit observations/trust-audit/mcp-server/avivsinai__langfuse-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 1fb851f74378 | CAUTION | B | 82 | first audit |
Questions
What is the Langfuse MCP server?
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
Is Langfuse safe to connect to an agent?
With care. The audit graded it B (82/100) and found 13 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Langfuse need?
It reads LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Langfuse run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as langfuse-mcp.
How current is this page?
The grade is for one exact copy of the source (1fb851f74378), read on 2026-10-07. The repository is watched and re-audited when it changes.