How to Use the Langfuse (LLM Tracing & Evals) MCP in Claude

Q: How do I debug Langfuse (LLM Tracing & Evals) traces in Claude Desktop?

Use the gettrace tool by pasting the trace ID directly into your chat. The MCP server will fetch the full telemetry graph, allowing you to inspect the inputs and outputs of every generation.

Q: Can Langfuse (LLM Tracing & Evals) track my Claude Desktop prompt versions?

Yes. The listprompts tool queries your Langfuse project to return all active templates. You can then review these versions inside the chat to ensure your code matches your production prompts.

Q: How does Langfuse (LLM Tracing & Evals) report costs to Claude Desktop?

Run getdailymetrics to pull your usage data. It returns the current USD spend and latency stats, giving you a snapshot of your LLM application's financial and performance impact.

Q: Where does the server store my API credentials?

Your keys live in your local claudedesktopconfig.json file. The server uses these to authenticate with the Langfuse API securely, and they never leave your machine.

Monitor your LLM production performance directly inside Claude Desktop with the Langfuse MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Langfuse (LLM Tracing & Evals) MCP to Claude Desktop

Create your Vinkius account to connect Langfuse (LLM Tracing & Evals) to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Langfuse (LLM Tracing & Evals) with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full trace visibility in Claude Desktop

Stop jumping between your terminal and the browser to debug failed LLM requests. Using `get_trace` and `list_traces`, you can pull the entire execution graph directly into your chat window to see exactly what happened under the hood. It’s about seeing the raw data while you work. When a request hangs, `get_observation` lets you drill into specific spans to identify which step of the chain is causing the latency.

Prompt and metric auditing for Claude Desktop

Keep your prompt templates synced without leaving your workflow. The `list_prompts` tool gives you instant access to your active versions, so you're always referencing the same logic running in production. Feedback loops matter. You can use `create_score` to log evaluation results or human feedback on specific interactions, ensuring your model improvements are backed by real data.

Daily performance tracking

Get a clear picture of your operational costs and latency spikes without digging through raw logs. The `get_daily_metrics` tool aggregates your usage data into a readable summary right where you're chatting. This is critical when you need to justify infrastructure spend or investigate performance regressions. You'll see the numbers you need to make decisions, formatted for quick analysis.

Setup guide

Set up Langfuse (LLM Tracing & Evals) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Langfuse (LLM Tracing & Evals) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Langfuse (LLM Tracing & Evals) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under langfuse-llm-tracing-evals-mcp.

json

{
  "mcpServers": {
    "langfuse-llm-tracing-evals-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Langfuse. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Langfuse (LLM Tracing & Evals) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Langfuse (LLM Tracing & Evals) MCP in Claude Desktop

Use the `get_trace` tool by pasting the trace ID directly into your chat. The MCP server will fetch the full telemetry graph, allowing you to inspect the inputs and outputs of every generation.

Yes. The `list_prompts` tool queries your Langfuse project to return all active templates. You can then review these versions inside the chat to ensure your code matches your production prompts.

Run `get_daily_metrics` to pull your usage data. It returns the current USD spend and latency stats, giving you a snapshot of your LLM application's financial and performance impact.

The server only touches your Langfuse trace, observation, and score data. It acts as a read-heavy proxy that requires your API keys to establish a connection, and no information is stored on our end.

Your keys live in your local `claude_desktop_config.json` file. The server uses these to authenticate with the Langfuse API securely, and they never leave your machine.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript