Documentation over MCP
Connect an AI assistant to these docs through the Model Context Protocol.
Guest Machines publishes its documentation as a remote Model Context Protocol server. Point any MCP client at it and your assistant can read these pages directly instead of guessing or scraping rendered HTML.
The server is public, unauthenticated, and read-only.
https://guestmachines.com/api/mcpIt speaks Streamable HTTP and holds no session state, so no configuration beyond the URL is needed.
Connect a client
For Claude Code:
claude mcp add --transport http gm-docs https://guestmachines.com/api/mcpFor clients configured through JSON, such as Claude Desktop, Cursor, or VS Code:
{
"mcpServers": {
"gm-docs": {
"type": "http",
"url": "https://guestmachines.com/api/mcp"
}
}
}Tools
| Tool | Purpose |
|---|---|
list_docs | Every page with its path, title, and summary |
get_doc | One page as Markdown, by path (developers/webhooks) or URL |
search_docs | Full-text search returning matching pages with excerpts |
The documentation is small enough to browse. Listing the pages and reading the ones that look relevant generally beats searching, and the tool descriptions say so — expect an assistant to start with list_docs.
Without MCP
The same content is available over plain HTTP, which is often enough:
| URL | Contents |
|---|---|
/llms.txt | An index of every page, for AI agents |
/llms-full.txt | The entire documentation as one Markdown file |
/docs/<page>.md | A single page as Markdown |
Any documentation URL also returns Markdown when the request sends Accept: text/markdown:
curl -H 'Accept: text/markdown' https://guestmachines.com/docs/developers/webhooks