Document Parser

Overview

Document Parser is a Model Context Protocol server that extracts structured data from PDF, Word, and HTML documents. It integrates directly into AI assistants as callable tools, letting Claude and other models parse and pull information from files on your behalf.

The server runs locally via the npm package @agenson-horrowitz/document-parser-mcp, communicating over stdio with no authentication required. Version v1.0.8 is available now under the MIT license, with source code at agenson-tools/document-parser-mcp on GitHub.

Document Parser lives in the File System category on mcp.site and works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and other MCP clients. If you maintain this project, claim your listing to earn the Verified badge and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "document_parser": {
      "command": "npx",
      "args": [
        "-y",
        "@agenson-horrowitz/document-parser-mcp"
      ]
    }
  }
}