How to Use the Braintrust MCP in OpenAI Agents SDK
Track production LLM evaluations directly inside your OpenAI Agents SDK workflow.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Braintrust MCP to OpenAI Agents SDK
Create your Vinkius account to connect Braintrust to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Record live experiment traces
Use `create_experiment` to log every step of your agent execution path. This captures exactly how your production pipeline performs under load. Your OpenAI Agents SDK instances push these logs to Braintrust immediately. You get an audit trail of every decision your agent makes during testing.
Manage prompt versions for OpenAI Agents SDK
Call `get_prompt` to pull the latest system instructions stored in your Braintrust account. You stop hardcoding strings in your Python files. Updating a prompt in the Braintrust dashboard reflects in your agent behavior instantly. It keeps your logic isolated from your deployment code.
Automate dataset testing
Run `insert_dataset_row` to feed agent outputs back into your evaluation matrix. You build a feedback loop that validates your agent against real data. This MCP server handles the handshake between your SDK and the Braintrust database. You focus on building the agent logic while the infrastructure tracks the accuracy.
Set up Braintrust MCP in OpenAI Agents SDK
Prerequisites
- Python 3.10+ installed
-
openai-agentspackage (pip install openai-agents) - Active Vinkius subscription with a valid endpoint token
- 1
Install the SDK
Run
pip install openai-agentsto install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed. - 2
Connect via SSE transport
Use
MCPServerSsewith your Vinkius endpoint URL. Replace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. The SDK auto-discovers all Braintrust tools at runtime. - 3
Create your Agent
Pass the MCP to
Agent(mcp_servers=[server]). The agent receives Braintrust tools as native definitions — JSON schemas resolve automatically. - 4
Run the agent
Call
Runner.run(agent, prompt)to execute. The agent invokes the appropriate Braintrust tools and returns structured results. Copy the full example on the right to get started.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse
async def main():
async with MCPServerSse(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as server:
agent = Agent(
name="Braintrust Agent",
instructions="You have access to Braintrust tools.",
mcp_servers=[server],
)
result = await Runner.run(agent, "List recent transactions")
print(result.final_output)
asyncio.run(main()) 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.
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 OpenAI Agents SDK
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Braintrust MCP today
We host it, we monitor it, we maintain it. You just paste one token.