How to Use the Braintrust MCP in Pydantic AI

Run type-safe Braintrust evaluations using Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Braintrust to Pydantic 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 Braintrust with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Braintrust prompts in Pydantic AI

Use `list_prompts` to pull versioned system prompts into your agent. Pydantic AI ensures the returned data matches your expected type definitions. If the prompt format changes, your agent throws an error immediately. You catch configuration drift before it reaches your users.

Insert rows with Pydantic AI validation

Call `insert_dataset_row` to save your agent results back to Braintrust. Pydantic AI validates the payload against your schema before the server transmits it. This prevents malformed data from polluting your evaluation records. You get clean metrics every time.

Retrieve ground truth in Pydantic AI

Run `list_datasets` to see which test banks are available for your evaluation run. You select the exact data needed for your current task. Your Pydantic AI agent uses these references to compare model output against known correct answers. It is the most reliable way to benchmark your code.

Setup guide

Set up Braintrust MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "braintrust-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Braintrust tools.",
)

result = await agent.run("List recent Braintrust transactions")
print(result.output)

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 Pydantic AI

You instantiate an MCPToolset and pass it to your Agent. Pydantic AI then validates every tool response against your defined models.

Yes, it raises a validation error if the MCP server sends unexpected data. This stops your agent from processing corrupted results.

It is, because the MCP server provides a standardized interface. You can swap out the underlying LLM without changing your Braintrust integration.

You use the experiment tools to track your agent performance. These logs will respect the schema constraints you define in your Pydantic models.

The server uses signed tokens to authenticate requests. Your sensitive dataset rows remain private and isolated within your Braintrust instance.

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

Mastra AI sdk-typescript

Start using the Braintrust MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started