Show HN: Long PDF Reader MCP | Hacker News Reader

Show HN: Long PDF Reader MCP

pageindex.ai

We’re building an MCP that lets you chat with long PDFs (e.g. textbooks with hundreds of pages) on platforms like Claude, Cursor, and other AI agents — without worrying about context limits.

Open articleView on HN

Interesting, is this based on an external Vector DB to store and process the PDF?

Thanks for the great question! We actually use a reasoning-based, vectorless approach. In short, it follows this process:

  1. Generate a table of contents (ToC) for the document.

  2. Read the ToC to select a relevant section.

  3. Extract relevant information from the selected section.

  4. If enough information has been gathered, provide the answer; otherwise, return to step 2.

We believe this approach closely mimics how a human would navigate and read long PDFs.

Sounds interesting, will try it out.

Thanks, any feedback is welcome!

Reply on news.ycombinator.com