filedone MCP

The filedone MCP server enables AI assistants to perform document and image processing tasks. It allows users to merge, split, compress, and convert PDFs, extract text via OCR, pull tables into spreadsheets, translate documents, and edit photos. The server supports authentication via filedone accounts or API keys and integrates with various AI clients like Claude, ChatGPT, and Cursor.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

OAuth sign-inEndpoint checked 2026-10-26Operated by filedone

MCP endpoint (Streamable HTTP)

https://api.filedone.ai/mcp

Vendor documentation

What you can do with it

Merge, split, compress, or convert PDF files
Extract text from scanned documents using OCR
Pull tables from documents into spreadsheets
Translate PDFs or fix photos

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http filedone-mcp https://api.filedone.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add filedone-mcp --url https://api.filedone.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable filedone-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "filedone-mcp": {
      "url": "https://api.filedone.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "filedone-mcp": {
      "type": "streamableHttp",
      "url": "https://api.filedone.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start filedone-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "filedone-mcp": {
      "type": "http",
      "url": "https://api.filedone.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http filedone-mcp https://api.filedone.ai/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "filedone-mcp": {
      "url": "https://api.filedone.ai/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "filedone-mcp": {
      "serverUrl": "https://api.filedone.ai/mcp"
    }
  }
}

Ground your agent in cited data

filedone MCP gives your agent tools. Koskamo gives it reviewed, cited facts to check its answers against. Add it as a second MCP server; public reads need no API key.

Connect Koskamo Browse datasets

See all 2,378

Do you run filedone MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing