--- date: 2025-06-28 title: Agentic Onboarding & Docs MCP Server description: Integrate Langfuse into your existing codebase using AI agents like Cursor, Claude Code, GitHub Copilot, and Windsurf. Powered by the new Langfuse Docs MCP server. author: Marc ogImage: /images/changelog/2025-06-28-agentic-onboarding-and-docs-mcp.png --- > **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com). To make the Langfuse docs more accessible to AI agents, we've added a new [MCP Server](/docs/docs-mcp). This server exposes relevant context from the Langfuse docs, GitHub Issues, and GitHub Discussions to your agent. Instead of manually integrating Langfuse into your existing codebase, you can now use agents like Cursor, Claude Code, GitHub Copilot, and Windsurf to automatically add tracing to your LLM applications. Thank you [@JohnRichardEnders](https://github.com/JohnRichardEnders) for your contribution to this! ## Getting started On the [Get Started page](/docs/get-started), you'll now find a new "✨ Agentic" tab that provides: - One-click MCP server installation for popular editors - Step-by-step setup instructions for Cursor, GitHub Copilot in VSCode, Windsurf, and other MCP clients - A ready-to-use prompt that you can copy and paste into your agent The agent will automatically: - Detect which LLM libraries you're using (OpenAI, Anthropic, LangChain, etc.) - Choose the appropriate Langfuse integration method - Add the necessary imports and configuration - Wrap your existing LLM calls with Langfuse tracing ## Try it out This feature is experimental, so results may vary depending on your codebase complexity. We'd love to hear your feedback and experiences on [GitHub](https://github.com/langfuse/langfuse/issues). ## Learn more - [Agentic Onboarding Guide](/docs/get-started) - [Langfuse Docs MCP Server](/docs/docs-mcp) - [MCP Reference](https://mcp.reference.langfuse.com) --- ## Agent Instructions This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2025-06-28-agentic-onboarding-and-docs-mcp.md`. ### Querying these docs If the answer is not on this page, query the documentation instead of guessing: - **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question: ```bash curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?" ``` - **Index of every page**: , with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt). ### Before writing Langfuse code - **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results. - **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application. - **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples. - **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api `) to read or write traces, prompts, datasets, and scores from the terminal. Found an error in these docs? Please open an issue at .