Braintrust
Query Braintrust experiments, logs, datasets, and prompts from your agent while you eval prompts and traces before release.
Overview
Braintrust is an MCP server for the Ship phase that lets agents query AI experiments, logs, datasets, and prompts on Braintrust.
What is this MCP server?
- Remote streamable-http MCP at api.braintrust.dev with optional EU region (-eu)
- Query experiments, logs, datasets, and prompts from the agent
- AI evaluation and observability platform surfaced over MCP
- Registry version 1.0.0; data plane region variable in manifest
- Supports pre-ship prompt and trace review for solo AI features
- Remote URL pattern https://api{region}.braintrust.dev/mcp with region '' (US) or '-eu'
- Streamable-http transport type in server manifest
What problem does it solve?
You cannot see whether prompt or agent changes actually improved quality because eval data lives in a separate Braintrust UI.
Who is it for?
Solo builders shipping LLM features who already use Braintrust and want eval and observability queries inside the IDE agent.
Skip if: Greenfield projects with no eval harness and no need to compare prompts or trace production-like runs.
What do I get? / Deliverables
After registering the Braintrust MCP remote, your agent can pull experiments, logs, datasets, and prompts into the same thread as your code changes.
- Agent-accessible queries against Braintrust experiments and logs
- Faster Ship-phase review of datasets and prompts alongside code
Recommended MCP Servers
Journey fit
Evaluation and observability belong on the Ship shelf because they gate whether an AI feature is ready to leave your machine. Testing is the canonical subphase for experiment comparison, log review, and dataset-backed regressions—not launch marketing.
How it compares
Braintrust observability MCP bridge, not a generic logging agent skill.
Common Questions / FAQ
Who is Braintrust MCP for?
It is for developers and indie AI builders on Braintrust who want Claude Code, Cursor, or similar agents to access experiments, logs, datasets, and prompts over MCP.
When should I use Braintrust MCP?
Use it during Ship testing when you are validating prompts, reviewing traces, or comparing experiment results before release.
How do I add Braintrust to my agent?
Add the streamable-http remote https://api.braintrust.dev/mcp or https://api-eu.braintrust.dev/mcp for EU, with Braintrust API credentials per your client’s MCP setup.