Skip to main content
Calibrate meets your AI coding agent where it already works — Claude Code, Cursor, Codex, Windsurf, and others. Install the skills once and your agent learns how to connect an agent, build test sets, run evaluations, and calibrate the LLM judges against human labels — driving Calibrate through the interface that fits your workflow.

Get started

Agent skills

Install evaluation expertise with one command. Your agent learns how to build test suites, design judges, and run evals on Calibrate.

Guided onboarding

Run /onboard and your agent walks you through setting up a complete evaluation from scratch — connect, test, run, calibrate.

MCP server

Connect the Calibrate MCP server for native tool access in Claude Code, Cursor, Codex, and other MCP clients.

CLI

The Calibrate CLI gives agents structured JSON output for scripting evaluations in any terminal.

How agents use Calibrate

Skills are the knowledge layer; the MCP server, CLI, and API are the execution layers underneath. Combine them — skills teach your agent what a good evaluation looks like, and the CLI (which the skills drive) runs it. The skills drive the cloud CLI, while the MCP server exposes the same operations as native tools — both wrap the public API, so you can mix and match against the same workspace.

Supported agents

All you need is a Calibrate API key — create one under Workspace settings → API keys (see the API keys guide).

Next steps

Install the skills

One command to teach your agent the full Calibrate evaluation loop.

Run guided onboarding

Go from nothing to a trustworthy first evaluation with /onboard.

Set up the MCP server

Config file locations for each client and platform.

Install the CLI

Install, authenticate, and run your first evaluation.