Tools Categories Trending New Compare

langfuse-mcp

langfuse-mcp

Active·★ 90·MIT·Updated 2026-05-22

★ Trending★ Observability★ Dev Tooling

A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

Langfuse MCP Server is a Model Context Protocol server for Langfuse observability. It provides 37 tools across 9 categories including traces, observations, sessions, exceptions, prompts, datasets, annotation queues, scores, and schema. It supports selective tool loading and read-only mode, and can be used with various MCP clients like Claude Code, Cursor, and Codex CLI.

#agent-skills#ai-agents#claude-code#codex#developer-tools#genai#langfuse#llm

$ Install

$ pip install langfuse-mcp

↗ Visit site ★ GitHub

01

Features

01Comprehensive observability tools (traces, observations, sessions, exceptions, prompts, datasets, annotation queues, scores, schema)

02Selective tool loading to reduce token overhead

03Read-only mode for safe access

04Dataset item upsert functionality

05Includes a skill with debugging playbooks

02

Compatibility

Claude Code

MCP Client

Verified via docs

Codex CLI

MCP Client

Verified via docs

Cursor

MCP Client

Verified via docs

03

Quick start

1

$ pip install langfuse-mcp

04

Use cases

↳Debug production errors by querying traces and exceptions

↳Analyze user sessions for performance optimization

↳Manage prompts and datasets for LLM evaluation

05

Alternatives

GitHub MCP Server★ 30.3k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

genai-toolbox★ 15.4k

MCP Toolbox for Databases is an open source MCP server for databases.

context-mode★ 16.0k

Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms

Auto-claude-code-research-in-sleep★ 11.0k

ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP

agents-best-practices★ 1.1k

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.

The agent environment for long-horizon work, continuity, and self-evolution.

fast-agent★ 3.8k

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support

awesome-claude★ 250

HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.

See all alternatives →

Related searches

langfuse-mcp Alternatives Best Observability Tools 2026 Open Source Observability langfuse-mcp Tutorial langfuse-mcp Vs Competitors agent-skills ai-agents claude-code

Comments

Log in to leave a comment

K
Kendall KimApr 6, 2026
Used this for automated prompt optimization pipelines, works exactly as expected
Casey LeeMar 23, 2026
The Langfuse API coverage includes prompts, datasets, and evaluations — very complete
D
Drew BrownMar 19, 2026
Querying Langfuse traces from within agent workflows closes a useful feedback loop
J
Justice PatelMar 5, 2026
Can now build agents that learn from their own past performance via trace analysis

On this page

01Features 02Compatibility 03Quick start 04Use cases 05Alternatives

Stats

GitHub Stars★ 90

Last commit1w ago

StatusActive

LicenseMIT

CategoryObservability

Trend (30d)

+3.6↑ 0.7%

Links

Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.

QYS GitHub Buy me a coffee ☕

Browse by Category

Code Assistant Workflow Automation RAG / Knowledge Base Multi-Agent Browser Automation LLM Infra Dev Tooling Observability

Not affiliated with Anthropic, OpenAI or Microsoft.