Fonto documentation for AI tools. Converts DITA XML to Markdown on demand.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
An MCP server that makes the Fonto XML documentation accessible to AI tools like Claude Code, Cursor, and Claude Desktop. Live at fonto-docs.elliat.nl.
The 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.
MCP (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:
| Tool | What it does |
|---|---|
search_fonto_docs | Search by keyword β returns matching pages with titles, descriptions, and slugs |
get_fonto_page | Fetch the full content of a page by its slug |
list_pages | List all pages matching a keyword, with full section hierarchy β useful for discovery |
| Resource | What it contains |
|---|---|
fonto://catalog | All ~2000 pages with real titles, product grouping, and ancestry paths |
You can then ask things like "How does addDocumentChangeCallback work?" and the AI will look it up in the live Fonto docs.
The server is already running at https://fonto-docs.elliat.nl/mcp β you just need to point your tool at it.
Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json globally):
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Once connected, ask your AI assistant:
The server also exposes a plain HTTP API if you want to use it without MCP:
GET /search?q={query} β search pages by keywordGET /page/{slug} β fetch a page as MarkdownGET /catalog β full page catalog grouped by section; add ?section={keyword} to filterThe 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 β 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.
PRs welcome. The XML-to-Markdown conversion in src/fonto.js handles two formats:
<topic>, <body>, <section> structure<type>, <members>, <description> structureIf you find pages that don't convert well, open an issue with the slug.
MIT
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/fonto-docs)<a href="https://allmcps.com/mcp/fonto-docs"><img src="https://allmcps.com/api/badge/fonto-docs?style=directory" alt="Fonto Docs on AllMCPs" /></a>