PDF parsing server with text extraction, metadata, search, images, and TOC via MCP
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。
npm install parseflow-core
npm install -g parseflow-mcp-server
# 或使用 npx
npx parseflow-mcp-server
import { PDFParser } from 'parseflow-core';
const parser = new PDFParser();
const text = await parser.extractText('document.pdf');
const results = await parser.search('document.pdf', '关键词');
import { WordParser } from 'parseflow-core';
const parser = new WordParser();
const result = await parser.extractText('report.docx');
const html = await parser.extractHTML('report.docx');
import { ExcelParser } from 'parseflow-core';
const parser = new ExcelParser();
const data = await parser.extractData('spreadsheet.xlsx');
const results = await parser.searchText('data.xlsx', '收入');
import { PowerPointParser } from 'parseflow-core';
const parser = new PowerPointParser();
const result = await parser.extractText('presentation.pptx');
const results = await parser.searchText('slides.pptx', '关键词');
在 claude_desktop_config.json 中添加:
{
"mcpServers": {
"parseflow": {
"command": "npx",
"args": ["-y", "parseflow-mcp-server"]
}
}
}
| 类别 | 工具 | 描述 |
|---|---|---|
extract_text | 提取文本(支持加密 PDF) | |
get_metadata | 获取元数据 | |
search_pdf | 全文搜索 | |
extract_images | 提取图片 | |
get_toc | 获取目录 | |
merge_pdf | 合并多个 PDF | |
split_pdf | 拆分为单页 | |
extract_pdf_pages | 提取指定页码 | |
add_watermark | 添加文字水印 | |
add_image_watermark | 添加图片水印 | |
remove_watermark | 移除水印(覆盖) | |
| Word | extract_word | 提取文本/HTML |
search_word | 文本搜索 | |
| Excel | extract_excel | 提取数据 |
search_excel | 单元格搜索 | |
| PPT | extract_powerpoint | 提取幻灯片 |
search_powerpoint | 幻灯片搜索 | |
| OCR | extract_ocr | 图片文字识别 |
search_ocr | OCR 文本搜索 | |
| AI | semantic_index | 文档向量索引 |
semantic_search | 语义相似搜索 | |
| 批量 | batch_extract | 批量提取多文件 |
batch_search | 批量搜索多文件 |
| 版本 | 功能 |
|---|---|
| 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 |
| v1.2.0 | 🎯 PowerPoint 支持 |
| v1.1.0 | 📝 Word + 📊 Excel 支持 |
| v1.0.0 | 📄 PDF 基础解析 |
MIT License - 详见 LICENSE
Made with ❤️ by Libres-coder
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y parseflow-mcp-serverMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-libres-coder-parseflow": {
"command": "npx",
"args": [
"-y",
"parseflow-mcp-server"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referenceparseflow-mcp-servernpmio.github.Libres-coder/parseflow works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.