# Use these docs with AI (/docs/ai)

## For AI assistants and crawlers [#for-ai-assistants-and-crawlers]

| URL | What it is |
| --- | --- |
| [`/llms.txt`](/llms.txt) | Index of every page with a one-line description ([llmstxt.org](https://llmstxt.org) format) |
| [`/llms-full.txt`](/llms-full.txt) | The full text of all docs in one file |
| `/docs/<page>.md` | Any page as Markdown — e.g. [`/docs/leads/prospector/search-prospects/manual-search.md`](/docs/leads/prospector/search-prospects/manual-search.md) returns every tab of that feature |
| `Accept: text/markdown` | Requesting any docs URL with this header returns Markdown instead of HTML |
| [`/openapi.json`](/openapi.json) | OpenAPI description of the public REST API, mirrored from the API on every docs build |
| [`/docs/mcp/tools`](/docs/mcp/tools) | Every MCP tool, generated from the live server definitions |
| [`/sitemap.xml`](/sitemap.xml) | Every page, for search engines |

Each page also carries `TechArticle` structured data and a `<link rel="alternate" type="text/markdown">` pointing at its Markdown.

## On every page [#on-every-page]

- **Copy for LLM** copies the page as Markdown. On a feature page it copies **every tab** — Guide, API, MCP and Examples — so an assistant gets the complete picture in one paste.
- **View as Markdown** opens the same text in a new tab.
- **Open in…** sends the page straight to ChatGPT, Claude and others.
- **Ask about this page** answers questions from the page’s own text.

## Let your assistant act, not just read [#let-your-assistant-act-not-just-read]

Reading docs tells an assistant *how*. Connecting the [MCP server](/docs/leads/prospector/search-prospects/manual-search/mcp) lets it actually do the work in your account — search prospects, reveal contacts, and more.