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

Q: How do I use Langfuse (LLM Tracing & Evals) tools in Cursor?

Add the server to your .cursor/mcp.json file. Once enabled, you can ask the Cursor agent to list traces or fetch specific observations using the provided tools.

Q: Can I push Langfuse (LLM Tracing & Evals) scores from Cursor?

Yes. You can use the createscore tool inside an agent chat to attach evaluation results to a trace ID, allowing you to track quality changes in real-time.

Q: How does Langfuse (LLM Tracing & Evals) help with Cursor debugging?

By fetching getobservation data, you can see the exact context window and LLM output that triggered an error, providing the agent with the precise data needed to correct your code.

Debug live LLM production data inside Cursor using 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 Cursor

Create your Vinkius account to connect Langfuse (LLM Tracing & Evals) to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live trace inspection for Cursor

The AI needs real context to write better code. When you're in Agent mode, you can call `get_trace` to pull actual production execution paths into your editor, letting the AI see exactly where your LLM logic is failing. Stop guessing why a prompt isn't working. By using `list_traces` to find recent sessions, you give your agent the concrete inputs and outputs it needs to fix your code.

Automated evaluation in Cursor

Validate your changes by pushing results back into your monitoring pipeline. The `create_score` tool lets you attach pass/fail metrics to traces as you test your code, turning your development process into a data-driven loop. It connects your local test runs to your production dashboard. By logging these scores, you verify that your new code actually improves model output quality.

Session management and context

Organize your debugging by looking at high-level user sessions. The `list_sessions` tool helps you group related traces, making it easier to find the specific interaction that triggered a bug. This keeps your context window clean. Instead of hunting through thousands of records, you pull the session data relevant to the specific feature you're building.

Setup guide

Set up Langfuse (LLM Tracing & Evals) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Langfuse (LLM Tracing & Evals) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Langfuse (LLM Tracing & Evals) transactions." If the MCP tools are loaded correctly, Cursor will call the Langfuse (LLM Tracing & Evals) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Add the server to your `.cursor/mcp.json` file. Once enabled, you can ask the Cursor agent to list traces or fetch specific observations using the provided tools.

Yes. You can use the `create_score` tool inside an agent chat to attach evaluation results to a trace ID, allowing you to track quality changes in real-time.

By fetching `get_observation` data, you can see the exact context window and LLM output that triggered an error, providing the agent with the precise data needed to correct your code.

It manages your trace telemetry, prompt templates, and evaluation scores. The server only transmits these structured records between your editor and the Langfuse API.

All communication between your editor and the Langfuse backend happens over HTTPS. Your API keys are used locally to authorize these requests, ensuring your session data remains private.

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