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

Q: How do I debug LangChain agent failures using Langfuse (LLM Tracing & Evals)?

Use the gettrace tool to fetch the full execution graph for a failed run. It shows you the nested tool calls and input history so you can pinpoint the exact chain step that crashed.

Q: Can Langfuse (LLM Tracing & Evals) help me optimize LangChain token usage?

Yes. Call getdailymetrics to generate aggregated latency and cost reports for your LangChain sessions. This data tells you which parts of your chain are the most expensive.

Q: How do I list my LangChain session history?

Use the listsessions tool. It returns a list of high-level user session entities that group your traces together for easier analysis.

Q: Does this MCP server support custom evaluation logic?

You can attach any numeric score to a trace using createscore. This works for both manual human feedback and automated pipeline evaluation metrics.

Trace your LangChain agent pipelines with the Langfuse (LLM Tracing & Evals) MCP Server. Debug multi-step reasoning in real time.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace your LangChain agent execution flow

Feed your agent's chain outputs directly into telemetry logs. Use `create_observation` to mark every step of your reasoning chain so you can see exactly where the logic drifts. Your agent can pull previous context using `get_trace` to verify state. This lets you inspect the exact prompt and model response that triggered a specific chain decision.

Manage Langfuse (LLM Tracing & Evals) scores

Program your agents to self-evaluate using `create_score`. When your chain finishes a task, it writes a quality metric back to the trace so you know if the output met your criteria. Use `list_scores` to audit these metrics across thousands of runs. It's the fastest way to spot regression in your agent's performance without leaving your code.

Monitor cost and prompt versions

Call `get_daily_metrics` to track your LangChain spend. You'll see exactly how many tokens your agents burn through every day, broken down by model and trace. Use `list_prompts` to sync your templates. Your agents can fetch the latest version of a prompt directly from the registry, ensuring they always use the current production configuration.

Setup guide

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

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Langfuse (LLM Tracing & Evals) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "langfuse-llm-tracing-evals-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Langfuse (LLM Tracing & Evals) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Use the `get_trace` tool to fetch the full execution graph for a failed run. It shows you the nested tool calls and input history so you can pinpoint the exact chain step that crashed.

Yes. Call `get_daily_metrics` to generate aggregated latency and cost reports for your LangChain sessions. This data tells you which parts of your chain are the most expensive.

All data sent from your LangChain agent is encrypted in transit and handled via your private endpoint token. The MCP server only processes the trace metadata and scores you explicitly provide.

Use the `list_sessions` tool. It returns a list of high-level user session entities that group your traces together for easier analysis.

You can attach any numeric score to a trace using `create_score`. This works for both manual human feedback and automated pipeline evaluation metrics.

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