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., "@doc-mcp-server analyze the document at /path/to/sales_report.xlsx"
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.
Make AI understand complex documents - MCP server solving AI context limitations
โ Smart Document Analysis - Auto-detect sections, handle merged cells
โ Multi-format Support - Excel (.xlsx, .xls) | PDF/Word in development
โ Precise Field Mapping - Field mapping table + section-level reading
โ High Performance - Structured caching + lazy loading
Related MCP server: mcp-excel
macOS / Linux (Recommended with pipx)
# Install pipx
brew install pipx # macOS
# or sudo apt install pipx # Ubuntu/Debian
# Install doc-mcp-server
pipx install doc-mcp-serverWindows
pip install doc-mcp-serverFor more installation options, see Full Installation Guide
Add to ~/.claude.json or your project's config file:
{
"mcpServers": {
"document-analyzer": {
"command": "doc-mcp-server"
}
}
}For detailed configuration, see Quick Start Guide
Installation Guide - Platform-specific installation steps
Update Guide - How to upgrade to the latest version
Quick Start - Configuration and basic usage
Usage Guide - Complete API and examples
Troubleshooting - Common issues and solutions
# 1. Analyze document structure
analyze_document(file_path="/path/to/document.xlsx")
# 2. Read specific section
read_section(file_path="/path/to/document.xlsx", section_name="Section 1")
# 3. Read single field
read_field(file_path="/path/to/document.xlsx", field_key="Section1_CompanyName")Tool | Description |
| Analyze document structure and generate metadata |
| Get cached document structure |
| Read specific field value |
| Read entire section data |
| Write field value (Excel only) |
| List all sections |
| List all fields |
| Export document structure |
Problem: Large Excel files consume massive tokens when directly read by AI
โ Traditional: Read entire 323-row Excel โ 15000+ tokens โ Often fails
โ Using MCP: Structured reading โ 2000 tokens โ 90%+ success rate
Performance Improvements:
๐ Token consumption reduced by 87% (15000 โ 2000)
โ Success rate improved from 30% to 90%+
โก Handles 323 rows ร 24 columns with 4249 merged cells
Report Issues: GitHub Issues
Contribute Code: CONTRIBUTING.md
MIT License - see LICENSE for details
Made with โค๏ธ by Yang Jiahui
This server cannot be deployed
High-fidelity PDF to structured Markdown conversion and document field extraction.
SaaS intelligence for AI agents. 5 unified tools cover 1,000+ services with 91-96% token savings.
Provide your AI coding tools with token-efficient access to up-to-date technical documentation forโฆ
Extract structured data points from research papers and other documents with an LLM.
