Getting started
CiteHawk measures how AI assistants mention and cite your brand every week. This guide gets you from zero to your first API call, then points you at the right way to connect your own AI.
1. Get an API key
Every CiteHawk workspace has its own API key. In the app, open Settings > API Keys and create a key. Keep it secret — it grants read access to that workspace's visibility data.
The same key authenticates all four connection methods below. Pass it as a Bearer token:
Authorization: Bearer YOUR_API_KEYA missing or invalid key returns 401 Unauthorized.
2. Choose how to connect
There are four ways to work with your data:
- REST API — call
https://www.citehawk.com/api/v1from any language or script. - MCP server — connect Claude, Cursor, or any MCP client and ask it about your visibility in natural language.
- Claude Code skill — an agentic GEO loop that reads your gaps and edits your own site repo to close them.
- ChatGPT Action — import the OpenAPI spec into a custom GPT (or any agent framework) to give it live access.
Which should I use?
| If you want to… | Use |
|---|---|
| Pull data into a script, dashboard, or backend | REST API |
| Ask Claude or Cursor about your visibility in chat | MCP server |
| Have an agent fix your site to close AI gaps | Claude Code skill |
| Give a custom GPT or agent framework live access | ChatGPT Action |
3. Your first call
Fetch the last 7 days of visibility metrics for your workspace with a single request:
Request
curl -H "Authorization: Bearer YOUR_API_KEY" \
"https://www.citehawk.com/api/v1/metrics?days=7"You get back your visibility timeseries plus the latest KPIs as JSON. See the REST API reference for every endpoint and parameter, or connect an AI directly via the MCP server.