MCP Document Analysis Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Document Analysis ServerSummarize the document report.pdf"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Document Analysis Server
A Model Context Protocol (MCP) server that provides document analysis capabilities to LLM applications. Supports PDF, DOCX, and plaintext extraction with chunking, summarization, and semantic search.
Features
Document Extraction - Parse PDF, DOCX, and TXT files into structured text
Smart Chunking - Split documents with configurable overlap for RAG pipelines
Semantic Search - Embed and search document chunks using Cohere Embed v3
Summarization - Generate document summaries with configurable detail level
Metadata Extraction - Extract titles, authors, dates, page counts
MCP Protocol - Full MCP compliance for integration with Claude, IDEs, and other MCP hosts
Related MCP server: doc-lib-mcp
Architecture
MCP Client (Claude, IDE, etc.)
│
│ MCP Protocol (JSON-RPC over stdio)
│
▼
┌─────────────────────────────┐
│ MCP Document Server │
├─────────────────────────────┤
│ Tools: │
│ ├── extract_text │
│ ├── chunk_document │
│ ├── search_chunks │
│ ├── summarize_document │
│ └── get_metadata │
├─────────────────────────────┤
│ Resources: │
│ ├── document://{path} │
│ └── chunks://{doc_id} │
├─────────────────────────────┤
│ Parsers: │
│ ├── PDFParser │
│ ├── DocxParser │
│ └── TextParser │
└─────────────────────────────┘Quick Start
Installation
git clone https://github.com/BabyChrist666/mcp-document-server.git
cd mcp-document-server
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txtUsage with Claude Desktop
Add to your Claude Desktop claude_desktop_config.json:
{
"mcpServers": {
"document-analysis": {
"command": "python",
"args": ["-m", "mcp_doc_server"],
"cwd": "/path/to/mcp-document-server"
}
}
}Usage with Claude Code CLI
claude --mcp-server "python -m mcp_doc_server"Tools
extract_text
Extract full text from a document file.
{
"name": "extract_text",
"arguments": {
"file_path": "/path/to/document.pdf"
}
}chunk_document
Split a document into overlapping chunks for RAG.
{
"name": "chunk_document",
"arguments": {
"file_path": "/path/to/document.pdf",
"chunk_size": 500,
"overlap": 50
}
}search_chunks
Semantic search across document chunks.
{
"name": "search_chunks",
"arguments": {
"query": "What are the payment terms?",
"doc_id": "contract_2024",
"top_k": 5
}
}summarize_document
Generate a summary of a document.
{
"name": "summarize_document",
"arguments": {
"file_path": "/path/to/report.pdf",
"detail_level": "brief"
}
}get_metadata
Extract document metadata (title, author, pages, etc.).
{
"name": "get_metadata",
"arguments": {
"file_path": "/path/to/document.pdf"
}
}Configuration
Variable | Description | Default |
| Cohere API key for embeddings and generation | Required |
| Cohere embedding model |
|
| Default chunk size in characters |
|
| Default overlap between chunks |
|
Testing
pytest tests/ -vTech Stack
Python 3.10+ - Runtime
MCP SDK - Model Context Protocol implementation
Cohere - Embeddings and generation
PyPDF2 - PDF parsing
python-docx - DOCX parsing
Pydantic - Data validation
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
The Needle MCP server enables semantic search on documents stored in files like PDFs, DOCX, and XLSX by connecting AI applications to external data sources. It provides capabilities to create and manage document collections, perform natural language searches on stored content, and retrieve relevant information without requiring exact keyword matches.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- FlicenseBqualityDmaintenanceA Model Context Protocol server that enables LLMs to extract and use content from unstructured documents across a wide variety of file formats.111-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server for ingesting, chunking and semantically searching documentation files, with support for markdown, Python, OpenAPI, HTML files and URLs.-
- AlicenseNot gradedqualityFmaintenanceA Model Context Protocol server that provides intelligent file reading and semantic search capabilities across multiple document formats with security-first access controls.7MIT
- FlicenseBqualityDmaintenanceA local document processing server that can index various document formats (PDF, DOCX, TXT, HTML) and answer questions based on their content using the Model Context Protocol.8-