Supports recognition and extraction of LaTeX mathematical equations from PDF documents
PDF Processor MCP Server
A Model Context Protocol (MCP) server for processing PDF documents with advanced features including LaTeX equation extraction. This server enables Claude to fetch, process, and extract information from PDF documents, including LaTeX mathematical equations.
Features
PDF fetching from URLs
Text extraction from PDFs
LaTeX equation recognition and extraction
Integration with Claude via MCP
Installation
Standard Installation
Installing for Claude Desktop/Claude Code
To use this MCP server with Claude Desktop or Claude Code:
Install the MCP CLI tools if not already installed:
pip install "mcp[cli]"Install the server using the MCP CLI tool:
mcp install /path/to/pdf_tool_server.py --with-editable /path/to/mcp_pdf_processorFor example, if you've cloned this repository to
~/mcp_pdf_processor
:mcp install ~/mcp_pdf_processor/pdf_tool_server.py --with-editable ~/mcp_pdf_processorFor development with the MCP Inspector:
mcp dev /path/to/pdf_tool_server.py --with-editable /path/to/mcp_pdf_processorIn Claude Desktop, you can now use the PDF_TOOLS server in your conversations with these commands:
/mcp PDF_TOOLS fetch_pdf url=https://example.com/document.pdf /mcp PDF_TOOLS process_pdf hash_id=<HASH_ID> extract_latex=true /mcp PDF_TOOLS read_processed_pdf filename=<FILENAME>
Usage
Running Standalone
Environment Variables
OUTPUT_DIR
: Directory to store processed PDFs (default:llm_output
)PYTHONPATH
: Set to the directory containing the mcp_pdf_processor package
Using with Claude
When the server is registered, you can ask Claude to:
"Fetch and analyze the PDF at [URL]"
"Extract LaTeX equations from the PDF at [URL]"
"Summarize the content of the PDF at [URL]"
Requirements
The server requires the following main dependencies:
Python 3.9 or higher
pymupdf
: PDF processing and text extractionmcp
: Model Context Protocol supportpydantic
: Data validation and serializationaiohttp
: Asynchronous HTTP client/servertorch
: For LaTeX equation extraction (optional)pix2tex
: For LaTeX equation recognition (optional)
See pyproject.toml
for the complete list of dependencies and version requirements.
Usage Examples
Here's a complete example workflow for using the PDF processor with Claude Desktop:
License
MIT
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
A Model Context Protocol server that enables Claude to fetch, process, and extract information from PDF documents, including LaTeX mathematical equations.
Related MCP Servers
- AsecurityAlicenseAqualityModel Context Protocol server that enables Claude Desktop (or any MCP client) to fetch web content and process images appropriately.Last updated -1106MIT License
- AsecurityAlicenseAqualityA Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots.Last updated -315,70416MIT License
- AsecurityAlicenseAqualityA Model Context Protocol server that enables Claude to perform advanced web research with intelligent search queuing, enhanced content extraction, and deep research capabilities.Last updated -391MIT License
- AsecurityAlicenseAqualityA Model Context Protocol (MCP) server that enables Claude or other LLMs to fetch content from URLs, supporting HTML, JSON, text, and images with configurable request parameters.Last updated -32MIT License