SylphxAI/pdf-reader-mcp
#615 of 783 by Stars among GitHub repos
📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.
About
The most-starred PDF MCP server on GitHub. One call turns any PDF into an Agent Document Twin — structured text, tables, trust signals, and source evidence you can search, crop, and cite.
⭐ Star this repo if agents should cite PDFs with proof, not guess from plain text.
PDFs are not text files. They are layout, pixels, tables, hidden text, scanned pages, and reading order that breaks the moment you flatten them.
Most PDF tools give agents a text dump. Tables disappear. Scanned pages go blank. Hidden text sneaks in. Citations become guesses. Then the model hallucinates — confidently.
PDF Reader MCP is built for the moment your agent needs to prove an answer, not just sound plausible.…
Excerpted from github.com/SylphxAI/pdf-reader-mcp
Latest metrics
| Stars | 825 | 2026-07-16 |
|---|---|---|
| Forks | 70 | 2026-07-16 |
| Commits | 422 | 2026-07-16 |
| Releases | 52 | 2026-07-16 |
| Watchers | 4 | 2026-07-16 |
| Open issues | 0 | 2026-07-16 |
| Open PRs | 1 | 2026-07-16 |