🚀 MCP Server for Document Processing

Source

This MCP server lets AI assistants access and search your private documents, codebases, and latest tech info. It processes Markdown, text, and PDFs into a searchable database, extending AI knowledge beyond training data. Built with Docker, supports free and paid embeddings, and keeps AI updated with your data.

Catalog onlyCatalog onlySTDIO

Overview

MCP Server is a document processing tool that implements a Model Context Protocol (MCP) server for processing Markdown and text files, chunking and tokenizing the content using embedding models.

To use MCP Server, clone the repository, set up your environment variables in a .env file, place your Markdown and text files in the data/ directory, and run the processing and server commands using Docker.

Processes Markdown and text files to generate embeddings. - Exposes processed content through MCP tools for easy retrieval. - Supports custom embedding models and configurations.

Document processing for search and retrieval applications.
Integration with Roo Code for enhanced content management.
Custom embedding for specialized document types.

Add to your AI client

Use these steps to connect 🚀 MCP Server for Document Processing in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server-donphi": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-donphi"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-server-donphi": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-donphi"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-server-donphi": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-donphi"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-server-donphi": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-donphi"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-server-donphi": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-donphi"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-server-donphi": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-donphi"
      ]
    }
  }
}

FAQ

What file types does MCP Server support?

By default, it supports Markdown (.md) and text (.txt) files, with the option to configure additional types.

Do I need an API key to use MCP Server?

An OpenAI API key is required for embeddings, while an Anthropic API key is optional for response generation.

Can I use my own embedding model?

Yes! You can implement a custom embedding function and configure it in the `.env` file.

Research and data