npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

intsig-acg_solution-doc-extraction-mcp

v1.0.0

Published

MCP server for IntSig intelligent document extraction service

Readme

IntSig Document Extraction MCP Server

智能文档抽取 MCP 服务 -- 将合合信息智能文档抽取能力以 MCP 协议接入大模型平台。

快速开始

NPX 方式(推荐)

在客户平台添加 MCP 服务时,使用如下 JSON 配置:

{
  "transport": "streamable_http",
  "url": "http://<YOUR_SERVER_HOST>:8000/mcp?app_key=<YOUR_APP_KEY>"
}

或者以 stdio 方式在本地运行:

{
  "mcpServers": {
    "doc-extraction": {
      "command": "npx",
      "args": ["-y", "intsig-acg_solution-doc-extraction-mcp"],
      "env": {
        "BASE_URL": "http://<EXTRACTION_SERVICE_HOST>:<PORT>",
        "TRANSPORT": "stdio"
      }
    }
  }
}

Docker / 服务端部署

# 安装
npm install -g intsig-acg_solution-doc-extraction-mcp

# 启动 HTTP 模式(对接客户平台)
APP_KEY="your-appkey" \
BASE_URL="http://extraction-service:8080" \
TRANSPORT="http" \
PORT=8000 \
doc-extraction-mcp

环境变量

| 变量 | 必填 | 说明 | 示例 | |------|------|------|------| | APP_KEY | 否 | MCP 服务自身的鉴权 key(HTTP 模式)。客户平台请求时需通过 header x-app-key 或 query ?app_key= 传递。不设置则不鉴权 | abc123 | | BASE_URL | 是 | 智能文档抽取私有化服务地址(内网直连,无需鉴权) | http://10.0.1.5:8080 | | TRANSPORT | 否 | 传输方式:stdio(默认)或 http | http | | PORT | 否 | HTTP 模式监听端口(默认 8000) | 8000 |

鉴权说明APP_KEY 仅保护 MCP Server 本身,防止未授权访问。智能文档抽取后端服务为内网私有化部署,MCP Server 调用时不带鉴权。

提供的工具

1. extract_document - 文档信息抽取

从 base64 编码的文件中提取结构化信息。

参数:

| 参数 | 类型 | 必填 | 说明 | |------|------|------|------| | file_base64 | string | 是 | Base64 编码的文件内容 | | file_name | string | 否 | 原始文件名(含扩展名) | | fields | string[] | 条件必填 | 待抽取的文本字段名列表(与 table_fields 至少填一个) | | table_fields | object[] | 条件必填 | 待抽取的表格定义列表(与 fields 至少填一个) |

2. extract_document_from_url - 从 URL 抽取文档信息

从 URL 下载文件并提取结构化信息。

参数:

| 参数 | 类型 | 必填 | 说明 | |------|------|------|------| | file_url | string | 是 | 文件的 HTTP/HTTPS URL | | fields | string[] | 条件必填 | 待抽取的文本字段名列表(与 table_fields 至少填一个) | | table_fields | object[] | 条件必填 | 待抽取的表格定义列表(与 fields 至少填一个) |

支持的文件格式: png, jpg, jpeg, doc, docx, pdf, ofd, xlsx, xls

使用示例

在大模型聊天窗口中,用户可以这样使用:

  • "请帮我从这份合同中提取甲方名称、乙方名称、合同金额和签署日期"
  • "从这份发票中提取发票号码、开票日期、合计金额"
  • "从这份采购单中提取商品名称、数量、单价的表格信息"

支持的传输方式

| 方式 | 说明 | 适用场景 | |------|------|----------| | stdio | 标准输入输出 | 本地 CLI 客户端(如 Claude Desktop) | | http (streamable_http) | HTTP 长连接 | 服务端部署,对接平台 | | http (sse) | Server-Sent Events | 兼容旧版 MCP 客户端 |

License

MIT