Who it is forA developer building a document pipeline who needs PDF text and tables extracted on their own server.
The problemCloud extraction APIs cost money per page and send private documents to third parties.
The outcomeA REST endpoint on localhost that returns structured text and Markdown tables from PDFs.
What you need first
- The paperpilot or paperpilot-mcp binary from GitHub Releases, or Rust 1.75+ to build from source
- An MCP client such as Claude Code, Codex, Cursor or Claude Desktop for agent use
- Node.js and pnpm only for the desktop app
Steps
- Install Paper Pilot from Releases or build the gateway from source
- Start the server with
paperpilot serve --port 7823 - Call it from Python, Node or an n8n HTTP node at localhost:7823
- For Open WebUI, follow the README's integration guide to use it as a Tika-compatible extraction server
Prompt for your agent
Start KrushnaVardhanReddy/PaperPilot's local REST API on port 7823 and write a <Python or n8n> step that sends <pdf> to it and saves the extracted text and Markdown tables.
Caveat. This card is written from the KrushnaVardhanReddy/PaperPilot README, not from a test run by Deduped. Before you start, make sure you have the paperpilot or paperpilot-mcp binary from GitHub Releases, or Rust 1.75+ to build from source. Check the repo for newer instructions before you rely on these steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for KrushnaVardhanReddy/PaperPilot and "Run a local PDF extraction API for Python, n8n or Open WebUI"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer