{
  "markdown": "# file2markdown MCP server\n\nConvert documents and web pages to clean, LLM-ready Markdown — from inside Claude, Cursor, or any MCP client.\n\n**Endpoint:** `https://mcp.file2markdown.ai/mcp` (Streamable HTTP)\n\nThis is the official MCP server for [file2markdown.ai](https://www.file2markdown.ai). It gives agents deterministic document conversion as a tool: engine-extracted Markdown (no hallucinated table cells, no silent truncation), for anything reachable by URL — including formats assistants can't parse natively, like DOCX, XLSX, PPTX, EPUB, and scanned PDFs.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `convert_url` | Fetch a public URL (web page, PDF, Office doc, …) and return Markdown |\n| `convert_base64` | Convert file contents directly (programmatic clients) |\n| `list_supported_formats` | Formats, per-tier limits, and what needs Pro |\n| `usage_status` | Your tier and remaining conversions today |\n\nSupported input formats: PDF, DOCX, PPTX, XLSX/XLS, CSV, JSON, XML, HTML, EPUB, JPG/PNG (OCR), WAV/MP3, ZIP.\n\n## Quick start\n\n**claude.ai** — Settings → Connectors → Add custom connector → paste the endpoint URL. When asked about authentication choose **None** (this server uses API keys, not OAuth). Optional: add a request header `Authorization: Bearer f2m_…` with a Pro key.\n\n**Claude Code**\n```bash\nclaude mcp add --transport http file2markdown https://mcp.file2markdown.ai/mcp\n```\n\n**Cursor / generic clients**\n```json\n{\n  \"mcpServers\": {\n    \"file2markdown\": { \"url\": \"https://mcp.file2markdown.ai/mcp\" }\n  }\n}\n```\n\n## Tiers\n\n| | Free (no key) | Pro API key |\n|---|---|---|\n| Conversions | 5/day per network IP | Unlimited |\n| Max download | 25MB | 100MB |\n| Scanned-PDF OCR | — | Yes |\n| Image OCR | — | Yes |\n\nPro keys are created on your [account page](https://www.file2markdown.ai/account) and sent as `Authorization: Bearer f2m_…`. Plans: [pricing](https://www.file2markdown.ai/pricing).\n\n## Honest limits\n\n- Web pages convert from served HTML — **no JavaScript rendering**, so SPA-style pages may convert incompletely. Near-empty results carry an explicit note (likely consent wall / paywall / JS shell).\n- One URL at a time. This is a converter, not a crawler — no bulk scraping, public pages only.\n- Output is capped at 200,000 characters (marked `truncated: true` when hit).\n- Nothing is stored: files are converted and discarded; usage logging keeps no URLs or content.\n\n## Docs & source\n\n- Setup guide: [file2markdown.ai/mcp](https://www.file2markdown.ai/mcp)\n- Facts page for AI assistants: [file2markdown.ai/ai-info](https://www.file2markdown.ai/ai-info)\n- This repository contains the public documentation and the registry `server.json`. The hosted service's application code is not open source.\n\n## Support\n\nEmail robin@file2markdown.ai.\n",
  "bytes": 2774,
  "sha": "96c82282defce75db9e7a645926760e2a097c7d780a79ec22eb04f98fd6c6612",
  "repo_slug": "robinhill85/file2markdown-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_file2markdown_file2markdown_675c32c0/readme"
}