> ## Documentation Index
> Fetch the complete documentation index at: https://penseapp.vercel.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Give your AI coding agents the tools and knowledge to evaluate AI agents on Calibrate through skills, MCP, CLI, or API

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

<CardGroup cols={2}>
  <Card title="Agent skills" icon="graduation-cap" href="/docs/agents/skills">
    Install evaluation expertise with one command. Your agent learns how to
    build test suites, design judges, and run evals on Calibrate.
  </Card>

  <Card title="Guided onboarding" icon="wand-magic-sparkles" href="/docs/agents/onboarding">
    Run `/onboard` and your agent walks you through setting up a complete
    evaluation from scratch — connect, test, run, calibrate.
  </Card>

  <Card title="MCP server" icon="plug" href="/docs/mcp/overview">
    Connect the Calibrate MCP server for native tool access in Claude Code,
    Cursor, Codex, and other MCP clients.
  </Card>

  <Card title="CLI" icon="terminal" href="/docs/cli/calibrate/overview">
    The Calibrate CLI gives agents structured JSON output for scripting
    evaluations in any terminal.
  </Card>
</CardGroup>

## 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.

| Layer      | Purpose                                                     | Installation                                                                                                        |
| ---------- | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |
| Skills     | Teach agents how to design and run evaluations on Calibrate | `npx skills add dalmia/calibrate-skills`                                                                            |
| MCP server | Gives agents native tools to manage agents, tests, and runs | `claude mcp add --transport http calibrate https://mcp.calibrate.artpark.ai/mcp --header "X-API-Key: your_api_key"` |
| CLI        | Runs evaluations from any terminal with JSON output         | `brew install dalmia/tap/calibrate`                                                                                 |
| API        | Direct HTTPS access for any language or runtime             | REST over HTTPS — see the [API reference](/docs/api-reference/introduction)                                              |

The [skills](/docs/agents/skills) drive the cloud [CLI](/docs/cli/calibrate/overview),
while the [MCP server](/docs/mcp/overview) exposes the same operations as native
tools — both wrap the [public API](/docs/api-reference/introduction), so you can mix
and match against the same workspace.

## Supported agents

| Agent          | Skills | MCP | CLI | API |
| -------------- | ------ | --- | --- | --- |
| Claude Code    | ✓      | ✓   | ✓   | ✓   |
| Cursor         | ✓      | ✓   | ✓   | ✓   |
| Codex          | ✓      | ✓   | ✓   | ✓   |
| Windsurf       | ✓      | ✓   | ✓   | ✓   |
| Claude Desktop | ✓      | ✓   | —   | ✓   |
| Any agent      | —      | —   | ✓   | ✓   |

All you need is a Calibrate API key — create one under
[**Workspace settings → API keys**](https://calibrate.artpark.ai/workspace-settings?tab=api-keys)
(see the [API keys guide](/docs/reference/api-keys)).

## Next steps

<CardGroup cols={2}>
  <Card title="Install the skills" icon="graduation-cap" href="/docs/agents/skills">
    One command to teach your agent the full Calibrate evaluation loop.
  </Card>

  <Card title="Run guided onboarding" icon="wand-magic-sparkles" href="/docs/agents/onboarding">
    Go from nothing to a trustworthy first evaluation with `/onboard`.
  </Card>

  <Card title="Set up the MCP server" icon="plug" href="/docs/mcp/installation">
    Config file locations for each client and platform.
  </Card>

  <Card title="Install the CLI" icon="terminal" href="/docs/cli/calibrate/overview">
    Install, authenticate, and run your first evaluation.
  </Card>
</CardGroup>