Parseflow MCP Server

Parseflow MCP server exists for a simple reason — assistants are far more useful when they can act on Parseflow directly instead of describing what you should do. PDF parsing server with text extraction, metadata, search, images, and TOC via MCP.

What you get

const parser = new PDFParser(); const text = await parser.extractText('document.pdf'); const results = await parser.search('document.pdf', '关键词'); ```

What the assistant can call

Once Parseflow is connected, these are the calls the assistant has available:

• GitHub — https://github.com/Libres-coder/ParseFlow
• PDF — extract_text
• Word — extract_word
• Excel — extract_excel
• PPT — extract_powerpoint
• OCR — extract_ocr
• v1.8.0 — 💧 PDF 水印（文字/图片水印）
• v1.7.0 — 📦 批量处理（并行处理多文件）
• v1.6.0 — 🧠 语义搜索（AI 向量嵌入）
• v1.5.0 — 📄 PDF 合并/拆分/提取
• v1.4.0 — 🔐 加密 PDF 支持
• v1.3.0 — 🔍 OCR 图片文字识别

Setting it up

npx on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Parseflow's toolset — GitHub, PDF, Word and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Libres-coder; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Parseflow.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the parseflow mcp server does with a few real requests.