PaperPilot 发布：纯 Rust 本地 PDF 引擎支持 MCPHacker News AIT2·开发与工程

PaperPilot 发布：纯 Rust 本地 PDF 引擎支持 MCP

原标题：PaperPilot – Zero-Cloud, Pure-Rust PDF Engine with WASM and MCP

68AI 研判分

PaperPilot 是一款基于 Rust 开发的零云端依赖 PDF 处理工具，通过 WASM、CLI 及桌面端多形态运行。其核心亮点在于提供原生 MCP 服务器接口，使 Claude Desktop 等 AI 智能体能直接调用合并、OCR 及压缩功能，且所有文件均在本地内存处理，确保数据隐私。

报道正文

本文目录11 个章节

PDF tools for your AI agent — and for you. Pure Rust. Runs locally. Files never leave your machine.

PaperPilot demo

Try it in your browser → · Download · Roadmap

PaperPilot is a PDF and document toolkit written in Rust. The same engine runs as:

Surface	Use it for
MCP server	Give Claude Desktop, Cursor, or any MCP client the ability to merge, split, OCR, and compress PDFs
CLI	Batch and scripted workflows
Browser (WASM)	Zero-install tools; files are processed in browser memory, nothing is uploaded
Desktop app	Tauri + Svelte GUI with viewer, markup, and diff
Local REST API	Call it from Python, Node, or n8n at `localhost:7823`

No Chromium, no C++ runtime, no cloud calls.

Quick start

1. Use it with Claude / Cursor (MCP)

Download paperpilot-mcp from Releases, then add it to claude_desktop_config.json:

JSON

{
  "mcpServers": {
    "paperpilot": {
      "command": "/path/to/paperpilot-mcp"
    }
  }
}

Restart Claude and try: "Merge these two PDFs and compress the result."

2. Use the CLI

BASH

# Merge
paperpilot merge --inputs doc1.pdf doc2.pdf --output merged.pdf

# Compress
paperpilot compress --input in.pdf --quality 75 --output compressed.pdf

# Rotate pages 1, 3–5 by 90°
paperpilot rotate --input in.pdf --pages 1,3-5 --angle 90 --output out.pdf

3. Use it in the browser

Go to usepaperpilot.com. Open your browser's Network tab while you work — you'll see no file uploads.

4. Build from source

BASH

git clone https://github.com/KrushnaVardhanReddy/PaperPilot.git
cd PaperPilot
cargo build --release -p paperpilot-cli -p paperpilot-mcp -p paperpilot-gateway

Desktop app:

BASH

cd apps/desktop && pnpm install && pnpm tauri dev

Requires Rust 1.75+, Node.js, and pnpm.

What it can do today (v0.6)

Organize: merge, split, rotate, delete pages, reorder pages, extract pages, booklet imposition, N-up grid Optimize: compress Extract: plain text, OCR (pure-Rust PaddleOCR via rten) Security: watermark, validate signatures, remove signatures, PII scan, deep sanitize Office data: Excel → JSON, Excel → CSV

Coming next (see ROADMAP.md):

v0.7: PDF ↔ Markdown / HTML / JSON
v0.8: PDF → Word / Excel / PowerPoint
v0.9: encrypt, decrypt, sign, redact, forms, annotations
v1.0: render, flatten, repair, compare, PDF/A, Bates numbering

Why another PDF tool?

Private by default. Everything runs locally or in your browser tab.
Agent-ready. MCP support is first-class, not an afterthought.
One engine, many surfaces. CLI, MCP, REST, WASM, and desktop share the same Rust core, so behavior is consistent.
Small and dependency-light. Pure Rust, built on lopdf, pdf_oxide, rten, and friends.

Benchmarks

Run cargo bench --workspace to reproduce. Methodology and results: SYSTEM_BENCHMARK_REPORT.md.

Architecture

文本

Desktop (Tauri) · CLI · REST (Axum) · MCP (stdio) · WASM (browser / edge)
                              │
                       Rust core workspace
   paperpilot-core · paperpilot-pdf · paperpilot-nlp · paperpilot-gateway
   paperpilot-mcp · paperpilot-wasm · paperpilot-storage

Embed in your own site

HTML

<script src="https://cdn.usepaperpilot.com/embed.js" data-tools="merge,compress,ocr"></script>
<div id="paperpilot-widget"></div>

Local REST API

BASH

paperpilot serve --port 7823
curl -X POST http://localhost:7823/api/v1/pdf/merge \
  -H "Content-Type: application/json" \
  -d '{"inputs": ["a.pdf", "b.pdf"], "output": "out.pdf"}'

Swagger docs at http://localhost:7823/docs.