jztan/pdf-mcp

Production-ready MCP server for PDF processing with intelligent caching. Extract text, search, and analyze PDFs with AI agents.

52
/ 100
Established

Implements full-text search with BM25 relevance ranking via SQLite FTS5, and extracts tables as structured data (headers + rows) detected from visible borders. Designed for Claude Desktop, Claude Code, VS Code Copilot, and other MCP clients—includes 7 specialized tools for paginated reading, metadata lookup, image extraction, and cache management to optimize token usage on large documents.

7 stars and 1,820 monthly downloads. Available on PyPI.

Maintenance 13 / 25
Adoption 12 / 25
Maturity 18 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Monthly downloads

1,820

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/jztan/pdf-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.