How to Use the Braintrust MCP in LangChain

Build complex evaluation chains in LangChain by pulling Braintrust projects directly into your reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Braintrust MCP to LangChain

Create your Vinkius account to connect Braintrust 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 Braintrust with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Braintrust evaluations into LangChain pipelines

Use `create_experiment` to kick off automated test runs from within your agentic workflows. You define the logic, and the server handles the state tracking for every step in your chain. This keeps your model benchmarks grounded in real data. You'll see exactly how each link in your chain performs without leaving your Python environment.

Manage prompts and datasets for LangChain agents

Call `get_prompt` to inject version-controlled system instructions into your agent's current task. It pulls the literal text template so you never have to hardcode your logic again. Then use `insert_dataset_row` to feed results back into your evaluation matrix. Your chain writes its own test cases as it runs, making iterative improvement a background process.

Monitor Braintrust configurations via LangChain

Run `list_env_vars` to peek at the API keys and gateway settings currently active in your environment. It gives your agents visibility into the infrastructure they rely on. This makes debugging failed tool calls dead simple. You'll know if a model is failing because of a bad key or an actual logic error in your chain.

Setup guide

Set up Braintrust 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 Braintrust 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({
    "braintrust-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 Braintrust 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 Braintrust. 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 Braintrust 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 Braintrust MCP in LangChain

Install the MCP adapters and point your client to the Vinkius endpoint. You'll pass the tools to your agent constructor so the model can trigger evaluation tasks on demand.

Yes, it records the output of your chains directly into projects. You use the tools to append results to a dataset and then review the performance metrics in your dashboard.

Absolutely. Your agent pulls the latest prompt version using the server tools whenever it needs to reset its context or try a different instruction set.

Your evaluation datasets and prompt templates stay in your isolated Braintrust environment. We use token-based authentication to ensure only your authorized agents access the records.

The server stores your logs within your project environment. It acts as a secure repository for your evaluation history, separate from your live application traffic.

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