Skip to content
Braintrust MCP Server

Braintrust MCP Server

by Braintrust
v1.0.0
Repository Docs
Developer ToolsDatabases & Data
braintrustevalsobservabilityllmopssql

Summary

Query Braintrust evals and production logs in SQL from your editor — compare experiments against a baseline, debug a bad trace, and hand a teammate a permalink.

Features

  • sql_query over experiments, datasets and production logs, with infer_schema first
  • summarize_experiment with optional baseline comparison
  • generate_permalink to share a finding straight out of the editor
  • resolve_object and list_recent_objects for navigating projects by name or URL
  • search_docs across Braintrust guides and the API reference
  • Hosted remote server with a separate EU data plane; API-key or OAuth 2.0 auth

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "Braintrust MCP Server" tools will be available.
{
  "mcpServers": {
    "braintrust-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.braintrust.dev/mcp"
      ]
    }
  }
}

Description

Braintrust is an evaluation and observability platform for LLM applications: you run experiments, score them, and ship logs from production into the same place. Its MCP server closes the loop by letting the agent that is writing the code also interrogate the results, without a context switch into the web UI.

The centre of it is sql_query, which runs SQL directly against experiments, datasets and logs, with infer_schema to discover the available fields first so the agent is not guessing at column names. summarize_experiment returns aggregate scores and can diff them against a baseline experiment, which is the question you actually want answered after a prompt change — did this get better, and by how much.

Around that sit the navigation tools: resolve_object converts between names and IDs and parses Braintrust URLs, list_recent_objects surfaces recently touched projects, experiments, datasets, prompts and functions, and generate_permalink produces a shareable link so a finding from an editor session can go straight into a pull request or a Slack thread. search_docs covers Braintrust's own guides and API reference, and search_patterns, new_pattern and update_pattern record recurring project patterns.

It is a hosted remote server at https://api.braintrust.dev/mcp, with an EU data plane at https://api-eu.braintrust.dev/mcp. Authenticate either with an API key as a bearer token or interactively through OAuth 2.0, no key configuration required.

The workflow it enables: debugging a production log without leaving the IDE, comparing two experiment runs, checking cost metrics per model, and sharing the evidence with a link rather than a screenshot.

Related MCP Servers

MCP: Resend

by Resend

New

Resend's official MCP server for transactional and marketing email — send, schedule and batch messages, manage templates, contacts, broadcasts, automations, domains and suppressions from an agent.

Developer Tools

MCP: Postman MCP Server

by Postman

New

Postman's official MCP server — reach your workspaces, collections, specs and environments from Claude Code, Cursor, VS Code or Copilot, in four tool tiers.

Developer Tools
1 views

MCP: Jupyter MCP Server

by Datalayer

New

Drive live Jupyter notebooks from an agent — read and edit cells, execute code, see rich outputs, and run against local JupyterLab or a cloud sandbox.

Developer Tools
1 views

MCP: deja-vu

by Vladislav Shulcz

New

Indexes the coding-agent sessions already sitting on your disk — months of history from before you installed it — and serves them back over MCP. 3.5 GB searched in ~1.5 ms, no LLM, no embeddings.

Developer ToolsDatabases & Data
1 views
Browse all MCP servers →