DocReaderMCP Server

A FastMCP server designed to read and stream various file formats commonly used in organizations (PDF, DOCX, Excel XLSX, CSV, TSV, TXT). It outputs formatted Markdown and supports both segment/page limits and item streaming.

Features

• Document Formats Supported:

  • PDF: Pages parsed and converted to text.

  • DOCX: Paragraphs segmented into logical page blocks.

  • Excel (XLSX/XLS): Targeted sheet names or first sheet parsed.

  • CSV & TSV: Tables outputted in Markdown format.

  • TXT: Plain text paginated into logical blocks.

• Reading Options:

  • Optional page_range parameter (e.g. 1-3, 2) to select specific pages.

  • Optional sheet_name parameter for Excel files.

• Streaming Options:

  • Text-Style Documents (PDF, DOCX, TXT): Streamed sentence-by-sentence.

  • Tabular Documents (Excel, CSV, TSV): Streamed row-by-row as Markdown table rows.

• Docker Ready: Built with python:3.13.3-slim.

Related MCP server: md-converter-mcp

Tools Reference

Installation & Setup

Local Run (Venv / System Python)

1. Install dependencies:

   pip install -r requirements.txt

2. Start the server in standard mode:

   python main.py run

   Or in development mode:

   python main.py dev

Running with Docker

1. Build and start the container:

   docker compose up --build

2. By default, the container mounts a local ./data directory to /data in the container. Put your organizational documents in ./data to read them via the container.