# MCP File Processor

> MCP File Processor is an open-source MCP server for files and documents. Local MCP server for extracting text, keywords and chunks from files for RAG. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, self-hosted
- **Repository:** https://github.com/opafex/opafex-mcps/tree/HEAD/packages/file-processor
- **MCP Registry name:** io.github.Opafex/mcp-file-processor
- **Categories:** [files and documents](https://ai-powered.com/categories/files-and-documents), [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm)
- **Listing updated:** 2026-11-18

## About

The tools in this Node.js server take file content directly (base64 for PDF and Word, raw text for the rest) rather than reading paths, which suits pipelines where an assistant already holds the data. Everything runs locally with no API keys.

It offers extract_text, extract_keywords (ranked by frequency with stop words removed, default 20), detect_language (code versus natural language, plus programming language), chunk_text (default 1,000 characters with 200 overlap) and an all-in-one process_file. A server_info tool and a supported-types resource list what is available. Formats include PDF, DOCX, CSV, JSON, Markdown, HTML, XML and several programming languages.

It needs Node.js 20 or newer, installs from npm as @opafex/mcp-file-processor and is MIT licensed. The same service class can also be imported as a library.

## Features

- **Text extraction:** Pull text, word count and page count from PDF, Word and text formats.
- **Keyword ranking:** Return the most frequent non-stop words.
- **Content type detection:** Tell code from prose and name the programming language.
- **Overlapping chunks:** Split text into chunks sized for embedding.
- **One-call pipeline:** process_file runs extraction, detection, keywords and chunking together.
- **Runs offline:** No API keys or external services.

## Good for

- Prepare documents for a RAG index
- Extract text from a PDF an assistant was handed
- Tag a document with its main keywords
- Chunk long text with overlap before embedding

## Install

### Claude Code (Terminal)

```sh
claude mcp add mcp-file-processor -- npx -y @opafex/mcp-file-processor
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mcp-file-processor": {
      "command": "npx",
      "args": [
        "-y",
        "@opafex/mcp-file-processor"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp-file-processor": {
      "command": "npx",
      "args": [
        "-y",
        "@opafex/mcp-file-processor"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp-file-processor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@opafex/mcp-file-processor"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcp-file-processor": {
      "command": "npx",
      "args": [
        "-y",
        "@opafex/mcp-file-processor"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcp-file-processor": {
      "command": "npx",
      "args": [
        "-y",
        "@opafex/mcp-file-processor"
      ]
    }
  }
}
```

## Tools

- `extract_text`: Extract text from a file
- `extract_keywords`: Ranked keywords from text
- `detect_language`: Detect code versus natural language
- `chunk_text`: Split text into overlapping chunks
- `process_file`: Extract, detect, rank keywords and chunk in one call
- `server_info`: Server metadata and registered tools

## FAQ

### Does it need API keys?

No, everything runs locally.

### Which Node version?

Node.js 20 or newer.

### What file types work?

PDF, DOC/DOCX, TXT, Markdown, CSV, JSON, HTML, XML and common code files.

### What licence?

MIT.

### Is MCP File Processor free?

Yes. MCP File Processor is open source, so you can use and self-host it for free.

### How do I add MCP File Processor to Claude Code?

Run this command in your terminal: claude mcp add mcp-file-processor -- npx -y @opafex/mcp-file-processor

### What are the best alternatives to MCP File Processor?

The closest alternatives to MCP File Processor are headroom, omniget, next-ai-draw-io, mcp-for-blender and Claude Code Ultimate Guide.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [headroom](https://ai-powered.com/mcp/headroom-3): headroom is an open-source MCP server for ai models and llm tooling.
- [omniget](https://ai-powered.com/mcp/omniget): omniget is an open-source MCP server for ai models and llm tooling.
- [next-ai-draw-io](https://ai-powered.com/mcp/next-ai-draw-io-2): next-ai-draw-io is an open-source MCP server for ai models and llm tooling.
- [mcp-for-blender](https://ai-powered.com/mcp/mcp-for-blender): mcp-for-blender is an open-source MCP server for design and media.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [unity-mcp](https://ai-powered.com/mcp/unity-mcp-2): unity-mcp is an open-source MCP server for ai models and llm tooling.
- [fastapi_mcp](https://ai-powered.com/mcp/fastapi-mcp): fastapi_mcp is an open-source MCP server for ai models and llm tooling.
- [tyk](https://ai-powered.com/mcp/tyk): tyk is an open-source MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/mcp-file-processor-2
