# AI use cases for Paper Pilot (KrushnaVardhanReddy/PaperPilot) Repo: [KrushnaVardhanReddy/PaperPilot](https://github.com/KrushnaVardhanReddy/PaperPilot) | Use cases: 3 | Page: https://dedupedai.com/use-cases/krushnavardhanreddy-paperpilot/ PaperPilot is a PDF and document toolkit written in pure Rust that runs locally, so files never leave your machine. The same engine works as an MCP server for coding agents, a CLI, a browser tool, a desktop app and a local REST API. It can merge, split, rotate, compress, OCR, watermark and extract text and tables from PDFs. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Give Claude Code or Codex local PDF tools over MCP: https://dedupedai.com/use-cases/krushnavardhanreddy-paperpilot/give-your-coding-agent-local-pdf-tools-over-mcp/ - Merge, compress and rotate PDFs in a script with the CLI: https://dedupedai.com/use-cases/krushnavardhanreddy-paperpilot/batch-merge-and-compress-pdfs-from-the-command-line/ - Run a local PDF extraction API for Python, n8n or Open WebUI: https://dedupedai.com/use-cases/krushnavardhanreddy-paperpilot/extract-pdf-text-for-open-webui-locally/ ## How to give Claude Code or Codex local PDF tools over MCP with Paper Pilot Repo: [KrushnaVardhanReddy/PaperPilot](https://github.com/KrushnaVardhanReddy/PaperPilot) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Add the Paper Pilot MCP server so your agent can merge, split, OCR and compress PDFs on your machine. **Who it is for:** A developer or analyst who asks an agent to handle PDFs but does not want the files sent to a web service. **The problem:** Most agent PDF workflows rely on online converters or ad hoc Python scripts that break on odd files. **The outcome:** An agent that can merge, split, OCR and compress PDFs through a local stdio server. ### Steps 1. Download paperpilot-mcp from the GitHub Releases page 2. Print a ready config for your agent with `paperpilot-mcp --client-config codex` (or claude-code, cursor, claude-desktop) 3. Merge the printed config into your agent's MCP settings and restart it 4. Try: Merge these two PDFs and compress the result ### Prompt to paste into your agent ```text Install KrushnaVardhanReddy/PaperPilot's paperpilot-mcp, add it to with the config from --client-config, then merge and and compress the result. Keep all files local. ``` ### 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. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/krushnavardhanreddy-paperpilot/give-your-coding-agent-local-pdf-tools-over-mcp/ ## How to merge, compress and rotate PDFs in a script with the CLI with Paper Pilot Repo: [KrushnaVardhanReddy/PaperPilot](https://github.com/KrushnaVardhanReddy/PaperPilot) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README Use the paperpilot CLI for repeatable batch jobs such as merging monthly statements or shrinking scans. **Who it is for:** An office worker or ops person who processes the same kinds of PDFs every week. **The problem:** Doing the same merge and compress steps in a GUI every week is slow and error prone. **The outcome:** A small script that merges, compresses and rotates PDFs the same way every time. ### Steps 1. Install the CLI from Releases or build it with cargo 2. Merge files with `paperpilot merge --inputs doc1.pdf doc2.pdf --output merged.pdf` 3. Shrink the result with `paperpilot compress --input in.pdf --quality 75 --output compressed.pdf` 4. Fix scanned pages with `paperpilot rotate --input in.pdf --pages 1,3-5 --angle 90 --output out.pdf` 5. Wrap the commands in a shell script for your weekly batch ### Prompt to paste into your agent ```text Write a shell script that uses KrushnaVardhanReddy/PaperPilot's CLI to merge every PDF in in name order, compress the result at quality 75 and save it as . ``` ### 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. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/krushnavardhanreddy-paperpilot/batch-merge-and-compress-pdfs-from-the-command-line/ ## How to run a local PDF extraction API for Python, n8n or Open WebUI with Paper Pilot Repo: [KrushnaVardhanReddy/PaperPilot](https://github.com/KrushnaVardhanReddy/PaperPilot) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Start Paper Pilot's local REST API and send it documents from your own scripts or automations. **Who it is for:** A developer building a document pipeline who needs PDF text and tables extracted on their own server. **The problem:** Cloud extraction APIs cost money per page and send private documents to third parties. **The outcome:** A REST endpoint on localhost that returns structured text and Markdown tables from PDFs. ### Steps 1. Install Paper Pilot from Releases or build the gateway from source 2. Start the server with `paperpilot serve --port 7823` 3. Call it from Python, Node or an n8n HTTP node at localhost:7823 4. For Open WebUI, follow the README's integration guide to use it as a Tika-compatible extraction server ### Prompt to paste into your agent ```text Start KrushnaVardhanReddy/PaperPilot's local REST API on port 7823 and write a step that sends 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. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/krushnavardhanreddy-paperpilot/extract-pdf-text-for-open-webui-locally/