{
  "markdown": "# fonto-docs-mcp\n\n[![Deploy to Cloud Run](https://github.com/DrRataplan/fonto-docs-mcp/actions/workflows/deploy.yml/badge.svg)](https://github.com/DrRataplan/fonto-docs-mcp/actions/workflows/deploy.yml)\n[![MIT License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n\nAn MCP server that makes the [Fonto XML documentation](https://documentation.fontoxml.com/) accessible to AI tools like Claude Code, Cursor, and Claude Desktop. **Live at [fonto-docs.elliat.nl](https://fonto-docs.elliat.nl/).**\n\nThe Fonto docs are rendered by a JavaScript SPA, which makes them impossible for AI to read directly. This server fetches the underlying XML and converts it to clean, readable Markdown on demand.\n\n## What is MCP?\n\nMCP (Model Context Protocol) is a standard way to give AI assistants access to external tools. Once you connect this server to your AI tool, it gains access to these tools and resources:\n\n| Tool | What it does |\n|---|---|\n| `search_fonto_docs` | Search by keyword — returns matching pages with titles, descriptions, and slugs |\n| `get_fonto_page` | Fetch the full content of a page by its slug |\n| `list_pages` | List all pages matching a keyword, with full section hierarchy — useful for discovery |\n\n| Resource | What it contains |\n|---|---|\n| `fonto://catalog` | All ~2000 pages with real titles, product grouping, and ancestry paths |\n\nYou can then ask things like *\"How does addDocumentChangeCallback work?\"* and the AI will look it up in the live Fonto docs.\n\n## Connect to your AI tool\n\nThe server is already running at `https://fonto-docs.elliat.nl/mcp` — you just need to point your tool at it.\n\n### Claude Code (CLI)\n\n```bash\nclaude mcp add --transport http fonto-docs https://fonto-docs.elliat.nl/mcp\n```\n\n### Cursor\n\nAdd to `.cursor/mcp.json` in your project (or `~/.cursor/mcp.json` globally):\n\n```json\n{\n  \"mcpServers\": {\n    \"fonto-docs\": {\n      \"type\": \"http\",\n      \"url\": \"https://fonto-docs.elliat.nl/mcp\"\n    }\n  }\n}\n```\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"fonto-docs\": {\n      \"type\": \"http\",\n      \"url\": \"https://fonto-docs.elliat.nl/mcp\"\n    }\n  }\n}\n```\n\n## Usage examples\n\nOnce connected, ask your AI assistant:\n\n- *\"Search the Fonto docs for documentsManager\"*\n- *\"Get the Fonto docs page for clearundostackfordocument-f0187fade723\"*\n- *\"How does addDocumentChangeCallback work according to the Fonto docs?\"*\n- *\"List all pages in the configure section\"*\n- *\"What upgrade guides are available?\"*\n\n## HTTP API\n\nThe server also exposes a plain HTTP API if you want to use it without MCP:\n\n- `GET /search?q={query}` — search pages by keyword\n- `GET /page/{slug}` — fetch a page as Markdown\n- `GET /catalog` — full page catalog grouped by section; add `?section={keyword}` to filter\n\n## How it works\n\nThe Fonto documentation site stores its content as XML at predictable URLs under `/static/xml/`. This server fetches those XML files directly and converts them to Markdown, bypassing the JavaScript rendering. Page content is never cached — every `get_fonto_page` call goes to `documentation.fontoxml.com` live. The page catalog (used by `list_pages` and `fonto://catalog`) is fetched once from the Fonto search index on first use and held in memory for the lifetime of the process.\n\n## Self-hosting\n\n```bash\nnpm install\nnpm start        # runs on port 8080 by default\nPORT=3000 npm start\n```\n\n## Contributing\n\nPRs welcome. The XML-to-Markdown conversion in `src/fonto.js` handles two formats:\n\n- **DITA guide pages** — `<topic>`, `<body>`, `<section>` structure\n- **API reference pages** — custom `<type>`, `<members>`, `<description>` structure\n\nIf you find pages that don't convert well, open an issue with the slug.\n\n## License\n\nMIT\n",
  "bytes": 3844,
  "sha": "b50c76c53c4cbc1b4d6cc9757bfd0291160b079236c1058204f85bb029f9012f",
  "repo_slug": "drrataplan/fonto-docs-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_drrataplan_fonto_docs_14ec074c/readme"
}