What does Langfuse Mcp do?
It is a TypeScript MCP server for the Langfuse Public API, enabling queries of traces, observations, sessions, scores, prompts, datasets, and metrics.
@hugoles
TypeScript MCP server for the Langfuse Public API with tools to query traces, observations, sessions, scores, prompts, datasets, and metrics from any MCP client.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"langfuse": {
"command": "npx",
"args": [
"-y",
"langfuse-mcp"
],
"env": {
"LANGFUSE_PUBLIC_KEY": "pk-lf-...",
"LANGFUSE_SECRET_KEY": "sk-lf-...",
"LANGFUSE_BASE_URL": "https://cloud.langfuse.com"
}
}
}
}List Langfuse traces with filters. Returns summary metadata (use getTrace for the full observation tree).
Fetch a single trace by id including all nested observations.
List observations (spans, generations, events) with filters.
Fetch a single observation by id.
List sessions within a time range.
Fetch a session by id, including its traces.
List scores with filters.
Fetch a single score by id.
List score configurations (definitions for score names, ranges, and categories).
Fetch a single score configuration by id.
List prompt definitions tracked in Langfuse.
Fetch a prompt by name. Optionally pin to a specific version or label (e.g. 'production').
List datasets configured in Langfuse.
Fetch metadata for a dataset by its name.
List items in a dataset (inputs / expected outputs / metadata).
Fetch a single dataset item by id.
List runs (evaluation rounds) for a dataset.
Fetch a specific dataset run by name.
Run a metrics query (counts, latency, cost, token usage). Pass a JSON query string per the Langfuse metrics API.
Fetch daily aggregated usage / cost / count metrics for traces and observations.
List models known to Langfuse (for cost / token attribution).
Fetch a single model definition by id.
List projects accessible to the current API key (typically a single project).
List comments attached to traces, observations, sessions, or prompts.
Fetch a single comment by id.
Fetch metadata for a media attachment (image, audio, file) by id.
Pings the Langfuse public health endpoint. Useful to validate credentials and connectivity.
A TypeScript MCP server that integrates with the Langfuse Public API, providing tools to query traces, observations, sessions, scores, prompts, datasets, and metrics from any MCP client.
—
It is a TypeScript MCP server for the Langfuse Public API, enabling queries of traces, observations, sessions, scores, prompts, datasets, and metrics.
Traces, observations, sessions, scores, prompts, datasets, and metrics.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
评论