How to Use the Braintrust MCP in Google ADK

Q: Can I filter the tools exposed to Google ADK?

You can use the toolnames filter during the McpToolset setup. This limits the agent to only the functions you want it to access.

Connect your Google ADK agents to Braintrust evaluation data.

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 Google ADK

Create your Vinkius account to connect Braintrust to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Braintrust datasets in Google ADK

Use `get_dataset` to pull specific evaluation schemas into your Gemini agent. You can now ground your responses in verified test data. The Google ADK framework handles the tool calls while this MCP server fetches the content. It turns your agent into a data-aware system.

List evaluation projects via Google ADK

Call `list_projects` to see what is currently running in your Braintrust workspace. You keep your agent aware of the broader evaluation environment. This visibility helps your Google ADK agent report back on the status of ongoing benchmarks. You don't have to switch tabs to check progress.

Map model metrics with Google ADK

Run `list_experiments` to retrieve past performance data for your models. You use this to inform the next steps in your agent's reasoning chain. Your Google ADK agent can now make decisions based on historical accuracy scores. It creates a smarter loop for your enterprise applications.

Setup guide

Set up Braintrust MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Braintrust tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Braintrust_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Braintrust tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You wrap the server in an McpToolset and pass it to your LlmAgent configuration. This exposes the Braintrust tools as native functions for your agent.

The MCP server acts as an interface layer for your agent. You can pull evaluation schemas from Braintrust and use them as context for your BigQuery queries.

Absolutely, as long as your agent provides the context. You can fetch large prompt templates using `get_prompt` and feed them directly into your Gemini model's window.

You can use the tool_names filter during the McpToolset setup. This limits the agent to only the functions you want it to access.

We enforce strict isolation between your Google Cloud data and the MCP connection. Only authorized tokens can read your Braintrust datasets.

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