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

Q: Can a CrewAI agent use Langfuse (LLM Tracing & Evals) to log custom metrics?

Yes. Your agents can call createobservation to log custom spans or events, and createscore to attach evaluation metrics to any active trace.

Q: How do I limit which tools on the CrewAI MCP Server can be accessed?

Use the MCPServerHTTP class from crewai.mcp and specify a toolfilter. This lets you restrict access, preventing junior agents from running administrative tools.

Equip your CrewAI agent teams with deep tracing and prompt management tools using 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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable cross-agent telemetry in CrewAI teams

Multi-agent teams generate a massive volume of nested calls that are incredibly difficult to debug. This MCP Server gives your crew the ability to inspect their own communication graphs and trace execution paths in real-time. A supervisor agent can call `list_traces` to see which sub-agents are stalling or failing. By querying `get_trace`, the supervisor gets the full nested execution tree to identify bottlenecks in the collaboration pipeline.

Centralize prompt management for specialized agents

Managing separate prompts for ten different agents in a crew is a maintenance nightmare. Instead of hardcoding instructions, you can store them centrally and let agents fetch their own configuration. Agents use `list_prompts` to pull their specific system instructions dynamically at runtime. If an agent's output needs adjustment, a moderator agent can call `create_score` to flag the trace for manual review.

Monitor execution costs across the entire crew

Running multiple autonomous agents can quickly drain your API budget if left unchecked. You need a way to monitor token usage and latency metrics programmatically. Use `get_daily_metrics` to pull rolled-up cost statistics directly into your crew's monitoring loop. If costs spike, you can call `list_sessions` to trace which specific run or user session caused the anomaly.

Setup guide

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

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Langfuse (LLM Tracing & Evals) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Langfuse (LLM Tracing & Evals) Analyst",
    goal="Access and analyze Langfuse (LLM Tracing & Evals) data via MCP.",
    backstory="Expert analyst with direct Langfuse (LLM Tracing & Evals) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Langfuse (LLM Tracing & Evals) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Langfuse (LLM Tracing & Evals) Analyst",
        goal="Access and analyze Langfuse (LLM Tracing & Evals) data via MCP.",
        backstory="Expert analyst with direct Langfuse (LLM Tracing & Evals) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Langfuse (LLM Tracing & Evals) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can pass the Vinkius HTTP endpoint directly into the agent's `mcps` parameter array. The MCP client handles the underlying request formatting automatically.

Yes. Your agents can call `create_observation` to log custom spans or events, and `create_score` to attach evaluation metrics to any active trace.

Use the `MCPServerHTTP` class from `crewai.mcp` and specify a `tool_filter`. This lets you restrict access, preventing junior agents from running administrative tools.

Yes. The server handles concurrent requests smoothly, allowing multiple agents to log telemetry and fetch prompts simultaneously without blocking your workflow.

Your telemetry data and evaluation scores are sent over secure, encrypted channels directly to your destination endpoint. Vinkius executes these requests in ephemeral, single-use runtimes that destroy all session state immediately after completion.

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