提供非结构化文档处理功能的模型上下文协议 (MLM) 服务器。该服务器使 LLM 能够提取并使用非结构化文档中的内容。
此 repo 工作正在进行中,请谨慎操作:)
支持的文件类型:
{".abw", ".bmp", ".csv", ".cwk", ".dbf", ".dif", ".doc", ".docm", ".docx", ".dot",
".dotm", ".eml", ".epub", ".et", ".eth", ".fods", ".gif", ".heic", ".htm", ".html",
".hwp", ".jpeg", ".jpg", ".md", ".mcw", ".mw", ".odt", ".org", ".p7s", ".pages",
".pbd", ".pdf", ".png", ".pot", ".potm", ".ppt", ".pptm", ".pptx", ".prn", ".rst",
".rtf", ".sdp", ".sgl", ".svg", ".sxg", ".tiff", ".txt", ".tsv", ".uof", ".uos1",
".uos2", ".web", ".webp", ".wk2", ".xls", ".xlsb", ".xlsm", ".xlsx", ".xlw", ".xml",
".zabw"}
先决条件:您需要:
非结构化 API 密钥。点击此处了解如何获取
本地安装的 Claude Desktop
关于如何将此 MCP 添加到您的 Claude 桌面的快速 TLDR:
克隆 repo 并设置 UV 环境。
在根目录中创建一个
.env文件并添加以下环境变量:UNSTRUCTURED_API_KEY。运行 MCP 服务器:
uv run doc_processor.py前往
~/Library/Application Support/Claude/并创建claude_desktop_config.json文件。在该文件中添加:
{
"mcpServers": {
"unstructured_doc_processor": {
"command": "PATH/TO/YOUR/UV",
"args": [
"--directory",
"ABSOLUTE/PATH/TO/YOUR/unstructured-mcp/",
"run",
"doc_processor.py"
],
"disabled": false
}
}
}
重启 Claude Desktop。现在您应该可以使用 MCP 了。
Appeared in Searches
- A server for unstructured data or information
- Metallurgical Engineering and Steel Plant Processing Information
- A file opener for reading PDF files, images, and other file types
- A tool for processing complex PDF documents with tables, charts, OCR, and images
- A powerful filesystem that works on both Windows and Mac