How to Use the Braintrust MCP in AutoGen

Let your AutoGen agents debate evaluation results using Braintrust as their source of truth.

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 AutoGen

Create your Vinkius account to connect Braintrust to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Braintrust findings in AutoGen

Assign one agent to call `list_experiments` and another to analyze the scores. They will argue over whether the latest model metrics meet your production standards. This forces your system to reconcile conflicting opinions on model quality. You get a consensus-driven report instead of a single, potentially biased analysis.

Update Braintrust records through AutoGen

Use `create_project` to spin up a new test environment when the agents decide a new experiment is needed. They handle the administrative setup of your evaluation infrastructure. It keeps your workspace organized without human intervention. Your agents track their own progress by creating and updating projects as they work through their tasks.

Negotiate Braintrust prompts with AutoGen

Call `list_prompts` to let your agents compare different system instructions. They challenge each other to find the version that produces the best output. This removes the guesswork from prompt engineering. Your agents perform the trial and error, settling on the most effective version based on your evaluation data.

Setup guide

Set up Braintrust MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Braintrust tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Braintrust_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Braintrust data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Braintrust_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Braintrust data")
    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 AutoGen

You pass the tool definitions to your AssistantAgent. The agents then decide when to call the server based on the progress of their current discussion.

It provides the raw data the agents argue about. By using the server, they ground their debate in actual evaluation results rather than assumptions.

Yes, they use the same shared MCP server to fetch projects and datasets. This ensures every agent in the group is looking at the same set of facts.

We enforce strict endpoint security on every request. Your evaluation metrics and prompt templates are never exposed outside of your authenticated group session.

The agents can only access the experiment logs, dataset rows, and prompt versions you allow. It is a strictly controlled read-and-write interface.

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