pdf-mcp
Reduces context waste and processing costs when AI agents analyze large PDFs by enabling semantic search and targeted extraction, eliminating the need to loa…
An MCP server that lets Claude Code and other AI agents work through large PDFs without overflowing their context — search by meaning or keyword, read only the pages that matter, and cleanly pull out tables, images, and scanned text, even from multi-column and Japanese layouts.
- Ask Claude to find relevant sections in a 500-page technical specification document by searching for meaning.
- Extract tables and structured data from financial reports without manually copying information.
- Retrieve specific content from scanned PDFs with Japanese text or complex multi-column layouts.
Reduces context waste and processing costs when AI agents analyze large PDFs by enabling semantic search and targeted extraction, eliminating the need to load entire documents into model context.
Engineering teams integrating Claude into document-heavy workflows like compliance review, specification analysis, or technical documentation processing.
https://github.com/jztan/pdf-mcp
By jztan
How to Get It
claude mcp add pdf-mcp -- npx -y pdf-mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
Once it’s connected, paste this into Claude:
Find relevant sections in a 500-page technical specification document by searching for meaning
Trust Signals Auto-scanned
Data & Access
Community Pulse Growing
Discussed on Hacker News
- McIntyre's Official Report to the UK Climategate Inquiry — Hacker News · 6 pts
- Department of Defense Guide: Detecting Agile BS — Hacker News · 5 pts
- X Corp., Plaintiff, vs. Media Matters for America and Eric Hananoki — Hacker News · 3 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 73 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 73 GitHub stars; contributors unknown; last commit 0d ago; license MIT.