How to Use the Braintrust MCP in Claude Code

Q: How do I view Braintrust projects in Claude Code?

Run a query and Claude Code will call listprojects to print your active evaluation projects. You can then pipe this list to other terminal tools.

Q: Can Claude Code add test cases to Braintrust?

Yes, it uses insertdatasetrow to append new evaluation rows. You can feed it raw JSON payloads directly from your terminal stdin.

Q: How does Claude Code fetch Braintrust prompts?

The agent invokes getprompt with the specific identifier. It prints the raw template text directly into your terminal or writes it to a file.

Q: Can I inspect environment variables?

Yes, the agent runs listenvvars to show your active gateway configurations. This is useful for verifying model routing keys in headless environments.

Drive Braintrust evaluations and prompt updates straight from your terminal with Claude Code and this MCP Server.

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 Code

Create your Vinkius account to connect Braintrust to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage prompts from the Claude Code terminal

The `list_prompts` tool lets Claude Code query your version-controlled system prompts directly from the CLI. You can view, compare, and pull active templates without leaving your SSH session or terminal pane. This makes prompt maintenance fast. Your agent pulls the latest template, runs a quick shell script to test it, and prepares the deployment.

Trigger Braintrust experiments in CI/CD pipelines

The `create_experiment` tool enables Claude Code to kick off evaluation runs inside headless environments using this MCP link. You can pipe terminal outputs directly into your historical test records during automated builds. It eliminates manual dashboard checks. The agent runs the pipeline, logs the experiment, and prints the pass/fail status directly to your terminal standard output.

Inspect evaluation datasets via this MCP Server

The `get_dataset` tool retrieves raw schemas and text banks directly to your shell. Claude Code uses this raw data to feed local test scripts or validate environment configurations before running a benchmark. You can easily grep through dataset fields or pipe them to other CLI utilities. It turns your evaluation data into a composable terminal resource.

Setup guide

Set up Braintrust MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see braintrust-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Braintrust transactions." It will automatically discover and invoke the available Braintrust tools.

Terminal

claude mcp add --transport http braintrust-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Braintrust MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "braintrust-mcp": {
      "type": "url",
      "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 Code

Run a query and Claude Code will call `list_projects` to print your active evaluation projects. You can then pipe this list to other terminal tools.

Yes, it uses `insert_dataset_row` to append new evaluation rows. You can feed it raw JSON payloads directly from your terminal stdin.

The agent invokes `get_prompt` with the specific identifier. It prints the raw template text directly into your terminal or writes it to a file.

Yes, the agent runs `list_env_vars` to show your active gateway configurations. This is useful for verifying model routing keys in headless environments.

Vinkius handles the authentication handshake using an isolated endpoint token. Your model API keys and prompt variables are never exposed to the shell history or stored in plaintext configuration files.

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