Use these docs from your AI tools
Connect Claude Code, Cursor, or VS Code to this guide so your assistant can search it and read its pages.
This guide has a read-only MCP server (the Model Context Protocol, a standard way for an AI assistant to use a service). Once you add it, your assistant can search the guide, list its pages, and read any page as Markdown, instead of guessing from memory. It needs no sign-in and sees no account data: only the pages anyone can read here.
The address is https://docs.<domain>/api/mcp. Replace <domain> with this site's domain.
Add it to your assistant
Claude Code
Run this once in a terminal, then check it with claude mcp list:
claude mcp add --transport http docs https://docs.<domain>/api/mcpAdd --scope project to save it in the project's .mcp.json so the whole team gets it, or
--scope user to have it in every project.
Cursor
Add the server to .cursor/mcp.json in your project, or to ~/.cursor/mcp.json for every project:
{
"mcpServers": {
"docs": { "url": "https://docs.<domain>/api/mcp" }
}
}VS Code
Add the server to .vscode/mcp.json in your workspace:
{
"servers": {
"docs": { "type": "http", "url": "https://docs.<domain>/api/mcp" }
}
}What your assistant can do
| Tool | What it does |
|---|---|
search | Finds pages and sections that match a question. Returns up to 10 results, each with the section it belongs to. |
list_pages | Lists every page with its address. |
get_page | Reads one page as Markdown, the same text as the page's "View as Markdown" link. |
Ask in plain words, such as "How do I invite a member to my organization?"; the assistant chooses the tool.
Not an AI tool? Use the Markdown links
Every page also has a "Copy for LLM" button and a Markdown version (add .md to its address).
/llms.txt lists all pages, and /llms-full.txt holds the text of every page in one file.