DocReaderMCP Server
Enables reading and streaming of organization document formats (PDF, DOCX, Excel, CSV, TSV, TXT) as Markdown, with support for page ranges and sheet selection.
README
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_rangeparameter (e.g.1-3,2) to select specific pages. - Optional
sheet_nameparameter for Excel files.
- Optional
- 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.
Tools Reference
| Tool Name | Parameters | Description |
|---|---|---|
read_pdf |
file_path (str), page_range (Optional[str]) |
Read PDF file pages |
stream_pdf |
file_path (str), page_range (Optional[str]) |
Stream PDF sentences |
read_docx |
file_path (str), page_range (Optional[str]) |
Read DOCX paragraphs by page |
stream_docx |
file_path (str), page_range (Optional[str]) |
Stream DOCX sentences |
read_excel |
file_path (str), sheet_name (Optional[str]) |
Read sheet to Markdown table |
stream_excel |
file_path (str), sheet_name (Optional[str]) |
Stream sheet row-by-row |
read_csv |
file_path (str) |
Read CSV to Markdown table |
stream_csv |
file_path (str) |
Stream CSV row-by-row |
read_tsv |
file_path (str) |
Read TSV to Markdown table |
stream_tsv |
file_path (str) |
Stream TSV row-by-row |
read_txt |
file_path (str), page_range (Optional[str]) |
Read TXT by page |
stream_txt |
file_path (str), page_range (Optional[str]) |
Stream TXT sentences |
Installation & Setup
Local Run (Venv / System Python)
- Install dependencies:
pip install -r requirements.txt - Start the server in standard mode:
Or in development mode:python main.py runpython main.py dev
Running with Docker
- Build and start the container:
docker compose up --build - By default, the container mounts a local
./datadirectory to/datain the container. Put your organizational documents in./datato read them via the container.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.