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

Q: How do I register this MCP Server with Mastra AI?

Install @mastra/mcp and instantiate the client with the server URL. You can then pull the tools using mcpClient.listTools() and spread them directly into your agent configuration.

Run self-healing Mastra AI workflows backed by real-time Langfuse tracing and evaluations via this 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 Mastra AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run self-healing Mastra AI MCP Server tasks

When an agent workflow fails, you need programmatic recovery, not just generic retries. This MCP Server lets your Mastra agents inspect their own execution history to make smart branching decisions on the fly. An agent can run `get_trace` to analyze why a previous step failed, then use that context to choose a different execution path. If a step requires explicit validation, the agent can call `list_scores` to verify if the previous output met quality thresholds before proceeding.

Manage prompt templates inside your workflow engine

Hardcoded prompts make workflows rigid and hard to update. By exposing your prompt registry to your agent, you can dynamically adjust instructions based on the current run context. Use `list_prompts` to fetch the latest version of a system prompt directly during workflow execution. If a run behaves unexpectedly, the agent can write an audit point using `create_observation` to log the exact span and generation details.

Track session state across multi-step runs

Complex workflows often span multiple days or dozens of steps. Keeping track of these long-running operations requires a persistent session model that ties individual steps together. Use `list_sessions` to group related traces under a single user identifier. When you need to analyze performance trends, `get_daily_metrics` provides a quick summary of latency and cost metrics across all active workflows.

Setup guide

Set up Langfuse (LLM Tracing & Evals) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Langfuse (LLM Tracing & Evals) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "langfuse-llm-tracing-evals-mcp-client",
  servers: {
    "langfuse-llm-tracing-evals-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Langfuse (LLM Tracing & Evals) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Langfuse (LLM Tracing & Evals) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Langfuse (LLM Tracing & Evals) transactions"
);
console.log(result.text);

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 Mastra AI

Install `@mastra/mcp` and instantiate the client with the server URL. You can then pull the tools using `mcpClient.listTools()` and spread them directly into your agent configuration.

Yes. You can configure your agent to evaluate its own responses and call `create_score` to attach a numeric rating or pass/fail flag directly to the active trace.

If a step fails, Mastra's built-in engine can retry with exponential backoff. During this process, you can call `list_observations` to verify if the failure was due to rate limits or bad model outputs.

Yes, Mastra supports tool approval gates. You can require manual confirmation before an agent calls tools on the MCP connection, ensuring complete control over your production database.

Your prompt templates and evaluation scores are processed inside isolated, ephemeral V8 containers. We use zero-trust network protocols to ensure your data is never cached or exposed to other tenants on the platform.

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