How to Use the Braintrust MCP in Claude

Q: How do I add the Braintrust MCP Server to my Claude Desktop app?

Open your claudedesktopconfig.json file and add the server configuration under the mcpServers block. Restart the desktop app, and you will see the Braintrust tools available via the hammer icon in your chat input.

Q: Can my agent run evaluations directly in the chat?

The agent uses createexperiment to spin up test runs and record historical traces of your pipeline. You get real-time tracking of evaluation scores inside your desktop chat interface as the run progresses.

Run Braintrust evaluations and pull test datasets directly inside your Claude Desktop chat.

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 Claude Desktop

Create your Vinkius account to connect Braintrust to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Braintrust projects inside Claude Desktop

This MCP Server lets your agent run `list_projects` and `create_project` to structure your evaluation workflows directly from the Claude Desktop chat window. Instead of copying project IDs back and forth between browser tabs, Claude pulls your Braintrust workspace structure straight into your local workspace. You configure the server via your local config file, giving Claude the exact context it needs to organize your model tests. The agent sets up new project environments on the fly, matching your local code changes to specific evaluation suites without manual web UI clicking.

Pinpoint LLM prompt shifts in Claude Desktop

The `get_prompt` and `list_prompts` tools expose your version-controlled prompt templates directly to your desktop agent. Claude pulls the exact system prompt and variable context you ran, letting you compare local code outputs against your production baselines without leaving the chat interface. By loading these templates into Claude Desktop, you debug prompt drifts instantly. Your local agent analyzes how minor tweaks to the system instructions affect model behavior, using the exact literal text stored in your Braintrust registry.

Push test cases to Braintrust datasets

The `get_dataset`, `list_datasets`, and `insert_dataset_row` tools let Claude Desktop manage your ground truth text banks. When you find a edge case in your local terminal, you tell Claude to append it to your test matrix. This setup bridges the gap between your local developer loop and central evaluation datasets. Your agent formats the raw text payload, verifies it matches your evaluation schema, and inserts the row directly via the MCP client's secure connection.

Setup guide

Set up Braintrust MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Braintrust MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Braintrust MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under braintrust-mcp.

json

{
  "mcpServers": {
    "braintrust-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Open your `claude_desktop_config.json` file and add the server configuration under the `mcpServers` block. Restart the desktop app, and you will see the Braintrust tools available via the hammer icon in your chat input.

Yes, you can connect this remote MCP server URL under the Custom Connectors section in your browser settings. This allows the web client to call Braintrust tools like `list_experiments` without running a local node process.

The server reads your API keys from your local environment or the secure configuration file. Claude Desktop passes these keys to the Braintrust AI Gateway securely via the `list_env_vars` endpoint when initiating runs.

The agent uses `create_experiment` to spin up test runs and record historical traces of your pipeline. You get real-time tracking of evaluation scores inside your desktop chat interface as the run progresses.

Your literal prompt text and test row matrices remain inside the V8 Isolate Sandbox. Claude Desktop communicates with Braintrust through an ephemeral MCP bridge, meaning your raw evaluation data never persists on third-party logging servers.

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