Intelligent Document Extraction - ComIDP MCP Server

@ComPDFKit

代码仓库

基本信息

分类

文件与存储

传输方式

stdio

作者

ComPDFKit

提交者

ComPDFKit-Youna

关于 Intelligent Document Extraction - ComIDP MCP Server

ComIDP MCP Server is a lightweight Model Context Protocol (MCP) server designed for seamless integrating ComIDP with AI chatbots, providing unstructured document processing functionalities, such as extracting data from PDF files. The service returns results in structured plain-te

#pdf-processing#ai-agent #data-extraction #ai-assistant

Intelligent Document Extraction - ComIDP MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "comidp-mcp": {
      "command": "uv",
      "args": [
        "run",
        "PATH/TO/comidp-mcp/src/virtual environment python",
        "PATH/TO/comidp-mcp/src/comidp_tools.py"
      ],
      "env": {
        "IDPKEY": "your_idp_key_here"
      }
    }
  }
}

Intelligent Document Extraction - ComIDP MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Intelligent Document Extraction - ComIDP?

Intelligent Document Extraction - ComIDP is a lightweight MCP server that integrates ComIDP’s intelligent document extraction capabilities with AI chatbots. It automatically extracts key information from unstructured PDF files, converts it into structured plain-text, and supports batch processing to improve document handling efficiency.

How to use Intelligent Document Extraction - ComIDP?

Setup requires Python 3.10+, pip, and uv. Configure Claude Desktop by editing claude_desktop_config.json with the command, arguments (pointing to the virtual environment’s Python and comidp_tools.py), and an IDPKEY environment variable. Use the data_extraction() function to process a list of PDF files or data_extraction_from_folder() to process all PDFs in a folder (with optional recursive search). Results are saved as TXT files in a specified output folder.

Key features of Intelligent Document Extraction - ComIDP

Extracts key information from PDF files.
Returns structured plain-text results in TXT format.
Supports batch processing of multiple files or folders.
Designed for seamless integration with AI chatbots.
Requires an IDPKEY API key for authentication.

Use cases of Intelligent Document Extraction - ComIDP

Automate data extraction from invoices, receipts, or contracts.
Process batches of PDF documents for downstream archival or analysis.
Provide structured data to AI chatbots for immediate user feedback.

常见问题

What dependencies are required to run the server?

Python 3.10 or higher, pip, uv, and a virtual environment. All required Python packages are listed in `requirements.txt`.

How do I configure Claude Desktop to use ComIDP MCP Server?

Edit `claude_desktop_config.json` to add a `comidp-mcp` server entry with the command `uv`, arguments pointing to the virtual environment’s Python and `comidp_tools.py`, and the `IDPKEY` environment variable set to your API key.

What file formats are currently supported for extraction?

Currently only PDF files are supported. Future updates will add support for JPG, PNG, and other formats.

How does data extraction work?

Two functions are provided: `data_extraction(filenames, save_dir_path, key, err_msg_lang)` for a list of PDF files, and `data_extraction_from_folder(folder, save_dir_path, recursive, key, err_msg_lang)` for a folder of PDFs. They return a dictionary mapping input paths to output TXT file paths.

Is a license required to use the server?

Yes, the project is licensed under Apache License 2.0. A trial license key is required; contact the team via the provided link to obtain one.

文件与存储分类下的更多 MCP 服务器

PDF Reader MCP Server (@shtse8/pdf-reader-mcp)

shtse8

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

810

drop.media

Upload once. Find, use and share across your AI workflows. drop.media is one media library for you and every AI agent you use: files added from Claude, ChatGPT, Cursor, the terminal or the web can be found, reused and sh