I-CAN-hack/pdf-mcp
PDF MCP server with image rendering capabilities. Useful for automatically searching datasheets, manuals, etc...
Leverages PyMuPDF and PyMuPDF4LLM to extract text in multiple formats (JSON, Markdown, HTML), render pages as configurable-DPI PNG images, and perform full-text search with context. Provides stateless tools for metadata extraction, table-of-contents parsing, and page-level access via stdio transport. Integrates with Claude and other MCP-compatible LLMs through standard `.mcp.json` configuration.
Stars
19
Forks
5
Language
Python
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/I-CAN-hack/pdf-mcp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
xt765/mcp_documents_reader
Model Context Protocol (MCP) server exposes tools to read multiple document types including...
ykarapazar/word-mcp-live
The only MCP server that edits Word documents while they're open — 114 tools, live editing,...
SylphxAI/pdf-reader-mcp
📄 Production-ready MCP server for PDF processing - 5-10x faster with parallel processing and...
aaronsb/texflow-mcp
LaTeX document compiler with MCP interface — AI agents author documents via structured model,...
nloui/paperless-mcp
An MCP (Model Context Protocol) server for interacting with a Paperless-NGX API server. This...