Langfuse MCP — Install & Live Demo

Name: Langfuse MCP MCP Server
Author: langfuse

Why use it

Key features

Prompt CRUD with version pinning
Trace lookup by id, user, session
Label-based prompt fetch (e.g. 'production')
Multi-project support per Langfuse workspace
Self-hosted or Langfuse Cloud

Live Demo

What it looks like in practice

langfuse-mcp.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "langfuse-mcp",
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "langfuse-mcp": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "@langfuse/mcp-server"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add langfuse-mcp -- npx -y @langfuse/mcp-server

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use Langfuse MCP

Iterate on a production prompt with traceable versions

👤 Prompt engineers ⏱ ~15 min intermediate

When to use: You want to A/B a prompt without leaving the chat.

Prerequisites

Server/skill installed and authenticated — See repo README

Flow

Pull the current production prompt

Get the 'support-triage' prompt labeled 'production' from Langfuse.✓ Copied

→ Current prompt text + version number
Test a tweak

Create version with my proposed change labeled 'staging'. Don't promote.✓ Copied

→ New version saved, 'production' label untouched

Outcome: Versioned, reviewable prompt history.

Pitfalls

Labels are mutable — Labels are mutable — moving 'production' to a new version is an instant rollout. Confirm before relabel.

Combine with: filesystem

Combinations

Pair with other MCPs for X10 leverage

langfuse-mcp + filesystem

Pair with filesystem for complementary capabilities

Use this server together with filesystem to complete a multi-step task.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
get_prompt	name, version\|label	Retrieve a prompt for inspection or copying	1 API call
create_prompt	name, prompt_text, labels	Save a new version	1 API call
list_traces	user_id\|session_id, limit	Debug a specific user/session	1 API call

Cost & Limits

What this costs to run

API quota: See provider docs for rate limits
Tokens per call: Varies by tool
Monetary: See repo README for pricing details
Tip: Cache tool results and avoid repeated identical calls.

Security

Permissions, secrets, blast radius

Credential storage: Use environment variables; never commit secrets

Data egress: Tool calls go to the provider's API as documented

Troubleshooting

Common errors and fixes

401 Unauthorized

Create a project in Langfuse, generate a key pair, set LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY.

Verify: get_prompt on a known name works

prompt not found

Prompts are project-scoped. Confirm LANGFUSE_HOST and that the prompt exists in the target project.

Verify: Open the Langfuse UI for that project

Alternatives

Langfuse MCP vs others

Alternative	When to use it instead	Tradeoff
comet-ml/opik-mcp	You already use Opik for tracing	Similar feature set; different vendor

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills