libres-coder avatar

Parseflow

libres-coder/parseflow

Gives Claude 23 tools to work with documents across PDF, Word, Excel, PowerPoint, and images. The PDF tools handle text extraction with multiple strategies, metadata retrieval, full-text search, image extraction, table of contents parsing, and document operations like merging, splitting, and watermarking. It supports encrypted PDFs with password handling. Office documents get their own extractors and search functions, while OCR handles 12 languages for image text recognition. The semantic search tools use vector embeddings for fuzzy matching without exact keywords. Batch operations let you process multiple files in parallel or recursively scan directories. Uses stdio transport, so you point it at local files on disk.

GitHub stars
2
tools
23
transport
STDIO
last updated
Dec 2, 2025

Tools

23 tools

Public tool metadata for what this MCP can expose to an agent.

extract_text提取文本(支持加密 PDF)

提取文本(支持加密 PDF)

No parameter schema in public metadata yet.

get_metadata获取元数据

获取元数据

No parameter schema in public metadata yet.

search_pdf全文搜索

全文搜索

No parameter schema in public metadata yet.

extract_images提取图片

提取图片

No parameter schema in public metadata yet.

get_toc获取目录

获取目录

No parameter schema in public metadata yet.

merge_pdf合并多个 PDF

合并多个 PDF

No parameter schema in public metadata yet.

split_pdf拆分为单页

拆分为单页

No parameter schema in public metadata yet.

extract_pdf_pages提取指定页码

提取指定页码

No parameter schema in public metadata yet.

add_watermark添加文字水印

添加文字水印

No parameter schema in public metadata yet.

add_image_watermark添加图片水印

添加图片水印

No parameter schema in public metadata yet.

remove_watermark移除水印(覆盖)

移除水印(覆盖)

No parameter schema in public metadata yet.

extract_word提取文本/HTML

提取文本/HTML

No parameter schema in public metadata yet.

search_word文本搜索

文本搜索

No parameter schema in public metadata yet.

extract_excel提取数据

提取数据

No parameter schema in public metadata yet.

search_excel单元格搜索

单元格搜索

No parameter schema in public metadata yet.

extract_powerpoint提取幻灯片

提取幻灯片

No parameter schema in public metadata yet.

search_powerpoint幻灯片搜索

幻灯片搜索

No parameter schema in public metadata yet.

extract_ocr图片文字识别

图片文字识别

No parameter schema in public metadata yet.

search_ocrOCR 文本搜索

OCR 文本搜索

No parameter schema in public metadata yet.

semantic_index文档向量索引

文档向量索引

No parameter schema in public metadata yet.

semantic_search语义相似搜索

语义相似搜索

No parameter schema in public metadata yet.

batch_extract批量提取多文件

批量提取多文件

No parameter schema in public metadata yet.

batch_search批量搜索多文件

批量搜索多文件

No parameter schema in public metadata yet.

Sponsors

Readme

📄 ParseFlow

AI 驱动的全能文档解析库

npm version MCP Server License: MIT

English | 中文


ParseFlow 是一个全面的文档解析解决方案,支持 PDF、Word、Excel、PowerPoint 和 图片 OCR。它提供独立的核心库和 MCP 服务器,可供 AI 助手使用。

✨ 功能特性

📄 PDF 支持

  • ✅ 多策略文本提取(原始、格式化、清理)
  • ✅ 按页或按范围提取
  • ✅ 🔐 加密 PDF 密码支持
  • ✅ 📄 PDF 合并、拆分、提取页面
  • ✅ 元数据获取、全文搜索

📝 Word / 📊 Excel / 🎯 PowerPoint

  • ✅ 文本提取和搜索
  • ✅ HTML 转换(Word)
  • ✅ 多工作表支持(Excel)
  • ✅ 幻灯片提取(PowerPoint)

🔍 OCR 图片识别

  • ✅ 支持 12 种语言
  • ✅ 图片文字提取和搜索

🧠 语义搜索

  • ✅ AI 向量嵌入
  • ✅ 智能文档搜索(无需精确关键词)

📦 批量处理

  • ✅ 并行处理多个文件
  • ✅ 目录递归扫描
  • ✅ 批量提取和搜索

🤖 MCP 服务器

  • ✅ 20 个 AI 助手工具
  • ✅ 支持 Claude Desktop、Windsurf、Cursor

📦 安装

核心库

npm install parseflow-core

MCP 服务器

npm install -g parseflow-mcp-server
# 或使用 npx
npx parseflow-mcp-server

🚀 快速开始

PDF 解析


View the full README on GitHub

Details

Repository
github.com/libres-coder/parseflow
Categories
Documents & Knowledge, Search & Web Crawling
Package
parseflow-mcp-server
Transport
STDIO
Registry
MCP registry, active

Related Documents & Knowledge MCP servers

View all
1superdocsapp avatarTypebar (formerly SuperDocs)superdocsapp/superdocs-pluginAI document editing: edits the exact section, leaves the rest. 38 MCP tools; agent self-signup.0stars
2dbsectrainer avatarMcp Legal Doc Analyzerdbsectrainer/mcp-legal-doc-analyzerDomain-specific MCP tooling for legal document workflows1stars
3duhokim avatarNebulamindduhokim/nebulamindAI astronomy wiki with open agent peer-review. Vote on evidence, propose edits, earn reputation.1stars
4tencent-lexiang avatarTencent Lexiang MCP Servertencent-lexiang/lexiang-mcp-serverTencent Lexiang AI knowledge base MCP server for searching, managing entries, and editing docs.1stars
5xiaojiou176-open avatarProvenote MCPxiaojiou176-open/provenoteFirst-party Provenote MCP server for drafts, research threads, auditable runs, and knowledge search.1stars
6joesaby avatarDoctree Mcpjoesaby/doctree-mcpBM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.1stars