---
date: 2025-11-20
title: Hosted MCP Server for Langfuse Prompt Management
description: Langfuse now includes a native Model Context Protocol (MCP) server with write capabilities, enabling AI agents to fetch and update prompts directly.
author: Michael
ogImage: /images/changelog/2025-11-20-native-mcp-server.png
canonical: /docs/api-and-data-platform/features/mcp-server
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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 canonical documentation for this feature (https://langfuse.com/docs/api-and-data-platform/features/mcp-server) and the API/SDK reference (https://api.reference.langfuse.com).

We're excited to announce that Langfuse now includes a **native MCP server** built directly into the platform. We release it with support for [Prompt Management](/docs/prompt-management/overview) and will extend it to the rest of the Langfuse data platform in the future.

Our previous Prompt MCP server ([changelog](/changelog/2025-02-16-mcp-server-update)) was a node package. The new one uses `StreamableHttp` to communicate with the Langfuse API directly, no need for building or installing any external dependencies.

**Update (May 2026):** The current MCP tool list, input schemas, and setup snippets now live in the generated [MCP Reference](https://mcp.reference.langfuse.com).

## What's New

The native MCP server launched at `/api/public/mcp` with five tools for comprehensive prompt management:

**Read Operations:**

- `getPrompt` - Fetch specific prompts by name, label, or version
- `listPrompts` - Browse all prompts with filtering and pagination

**Write Operations:**

- `createTextPrompt` - Create new text prompt versions
- `createChatPrompt` - Create new chat prompt versions (OpenAI-style messages)
- `updatePromptLabels` - Manage labels across prompt versions

## Setup

Simply configure your MCP client with BasicAuth credentials:

```bash
# Claude Code - one command
claude mcp add --transport http langfuse https://cloud.langfuse.com/api/public/mcp \
    --header "Authorization: Basic {your-base64-token}"
```

The native server uses a stateless architecture, ensuring clean separation between projects and reliable operation across all deployment types (Cloud, self-hosted, or local development).

See [documentation](/docs/api-and-data-platform/features/mcp-server) for more details.

## Feedback

We'd love to hear about your experience with the Langfuse MCP server. Share your feedback, ideas, and use cases in our [GitHub Discussion](https://github.com/orgs/langfuse/discussions/10605).

## Get Started

- [MCP Server Documentation](/docs/api-and-data-platform/features/mcp-server) - Complete setup guide
- [MCP Reference](https://mcp.reference.langfuse.com) - Current tools, setup snippets, schemas, and generated requests
- [Prompt Management with MCP](/docs/prompt-management/features/mcp-server) - Prompt-specific workflows

<!-- agent-instructions -->

---

## 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/2025-11-20-native-mcp-server.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**: <https://langfuse.com/llms.txt>, 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 <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.