How to Use the Langfuse (LLM Tracing & Evals) MCP in VS Code Copilot

Q: How do I integrate Langfuse (LLM Tracing & Evals) into VS Code?

Define the server in your .vscode/mcp.json file. This allows all team members to access the tools via the Copilot Chat agent once the configuration is committed.

Q: Does Langfuse (LLM Tracing & Evals) support team-wide VS Code config?

Absolutely. By committing the .vscode/mcp.json file to your repository, you ensure that every developer on your team has immediate access to the same tracing and evaluation tools.

Q: Can I list Langfuse (LLM Tracing & Evals) traces in VS Code?

Yes. Use the listtraces tool to see recent LLM sessions. This is useful for quickly identifying which users or requests are hitting your API during a production incident.

Monitor production LLM traffic directly in VS Code 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 VS Code Copilot

Create your Vinkius account to connect Langfuse (LLM Tracing & Evals) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-wide observability in VS Code

Commit your MCP configuration to the repo so everyone on your team has the same debugging tools. Using `list_traces` and `get_trace`, your entire engineering group can inspect production failures without leaving the editor. It creates a shared standard for how you analyze LLM performance. When someone finds a bug, they can share the exact trace ID for the rest of the team to inspect in their own VS Code instance.

Prompt version control for VS Code

Sync your prompt management with your codebase. The `list_prompts` tool lets you verify which template versions are currently active, preventing configuration drift across team environments. It ensures you're always testing against the same prompts used in production. You can quickly pull the latest template and compare it against your local changes.

Automated evaluation via VS Code

Standardize how your team logs quality metrics. By using `create_score`, any developer can run local evaluations and push the results to your dashboard, ensuring consistent feedback loops across the organization. This makes monitoring a collective effort. You can programmatically attach scores to traces during CI/CD checks, giving you visibility into the quality of every deployment.

Setup guide

Set up Langfuse (LLM Tracing & Evals) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Langfuse (LLM Tracing & Evals) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Langfuse (LLM Tracing & Evals) tools listed. Try asking: "List my recent Langfuse (LLM Tracing & Evals) transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Define the server in your `.vscode/mcp.json` file. This allows all team members to access the tools via the Copilot Chat agent once the configuration is committed.

Absolutely. By committing the `.vscode/mcp.json` file to your repository, you ensure that every developer on your team has immediate access to the same tracing and evaluation tools.

Yes. Use the `list_traces` tool to see recent LLM sessions. This is useful for quickly identifying which users or requests are hitting your API during a production incident.

The server only processes your trace telemetry and evaluation scores. We do not log your code or any sensitive source files; the tools only interact with the Langfuse API.

The server uses your provided API keys to create a secure, authenticated channel to your project. No third-party access is granted, and all data transfers are strictly scoped to the tools provided.

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