file2markdown MCP Server已验证已精选

@Robinhill85

代码仓库主页文档

基本信息

分类

数据与分析

作者

Robinhill85

提交者

Robinhill85

关于 file2markdown MCP Server

Official MCP server for file2markdown.ai — convert documents and web pages to clean Markdown inside Claude, Cursor, or any MCP client

#markdown #AI

file2markdown MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "file2markdown": {
      "url": "https://mcp.file2markdown.ai/mcp"
    }
  }
}

file2markdown MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,直接连接服务器端点实时获取工具列表。

概览

What is file2markdown?

The official MCP server for file2markdown.ai — it gives Claude, Cursor, and any MCP client deterministic document conversion as a tool. Engine-extracted Markdown (no hallucinated table cells, no silent paraphrasing) for anything reachable by URL, including formats assistants can't parse natively: DOCX, XLSX, PPTX, EPUB, and scanned PDFs via OCR.

How to use file2markdown?

No install and no signup — it's a hosted remote server. Add the endpoint https://mcp.file2markdown.ai/mcp to your client (in claude.ai: Settings → Connectors → Add custom connector, authentication: None). The free tier works immediately; a Pro API key sent as an Authorization: Bearer f2m_… header removes the daily limit and enables OCR. Full setup guide: file2markdown.ai/mcp

Key features of file2markdown

convert_url — fetch any public URL (web page, PDF, Office doc) and get clean Markdown back
convert_base64 — convert file contents directly, for programmatic clients
Deterministic extraction: real engines (pdf-inspector, MarkItDown), not model regeneration — exact tables, complete text
OCR for scanned PDFs and images (Pro)
Free tier with zero configuration: 5 conversions/day per network, no account needed
Privacy: files are converted and discarded; usage logging stores no URLs or content

Use cases of file2markdown

Convert a PDF, DOCX, or spreadsheet link to Markdown mid-conversation without leaving Claude
Feed clean Markdown into RAG pipelines and knowledge bases from agent workflows
Pull article-style web pages into notes as Markdown (no JavaScript rendering — SPA pages may convert incompletely)
Extract text from scanned documents via OCR in automated pipelines

常见问题

Is it free?

Yes — 5 conversions/day per network with no key or account. Pro ($15/mo, or $9/mo billed annually) removes the limit and adds OCR. Keys: [file2markdown.ai/account](https://www.file2markdown.ai/account)

Does it render JavaScript or crawl sites?

No. It converts the HTML a server sends, one URL at a time — it's a converter, not a crawler. Near-empty results carry an explicit note (likely consent wall, paywall, or JS-only page).

Where is the source code?

The hosted service's application code is not open source; the public repo at [github.com/Robinhill85/file2markdown-mcp](https://github.com/Robinhill85/file2markdown-mcp) carries the documentation and the registry `server.json`.

数据与分析分类下的更多 MCP 服务器

SiteGuru

Your site's real SEO data in your AI assistant. SiteGuru crawls your website and connects to Google Search Console and Google Analytics. This server exposes that data to your assistant, so you can ask what's broken, wha

Instagram MCP Server

HasData

Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.

Convertlyft

Website analytics and SEO in one. Every visit counted, no sampling. Each to-do says what leaked and the change to make, with the numbers behind it, you can visit us on Convertlyft.com first 5,000 Visits to your website f

Ultimate Web Scraper

Extract products, prices, images and reviews from any page in one click — or connect your AI agent and let it do the scraping for you. Works great for: - Ecommerce: extract every product from a Shopify, WooCommerce or

YouTube MCP Server