langfuse-mcp and mcp
About langfuse-mcp
avivsinai/langfuse-mcp
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
Exposes 25 tools across traces, observations, sessions, exceptions, datasets, and prompt management—significantly broader than prompt-only alternatives. Implements selective tool loading to minimize token overhead and read-only mode for safer access, with stdio transport integration for Claude Code, Codex CLI, and Cursor. Includes bundled debugging playbooks via a skill system and supports both cloud and self-hosted Langfuse instances.
About mcp
MicrosoftDocs/mcp
Official Microsoft Learn MCP Server – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.
Exposes semantic search and retrieval across Microsoft's official documentation and code samples through three MCP tools (`microsoft_docs_search`, `microsoft_docs_fetch`, `microsoft_code_sample_search`), accessible via HTTP endpoint or CLI. Includes experimental OpenAI-compatible endpoint support and token budget controls for cost management. Ships with portable Agent Skills that guide Claude, Cursor, and other MCP-compatible clients on when to invoke documentation lookups versus code reference queries.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work