Skip to main content

基于智谱 GLM-4V 的 PDF 视觉分析 MCP 工具

Project description

📄 MCP PDF Pro - 智能视觉分析工具

这是一个基于 Model Context Protocol (MCP) 的 PDF 分析工具。它能通过 AI 视觉模型(如智谱 GLM-4V、GPT-4o)“看懂” PDF 中的流程图、表格和图片。

🚀 安装与使用

本工具支持 代码与配置分离。作为使用者,你无需修改代码,只需在 Cursor/Claude 中配置自己的 API Key 即可。

1. 配置 Cursor (推荐)

请将以下内容添加到你的 Cursor settings.jsonmcpServers 字段中:

{
  "mcpServers": {
    "PDFPro": {
      "command": "uvx",
      "args": [
        "--from",
        "/这里填你whl文件的绝对路径/mcp_pdf_pro-0.1.0-py3-none-any.whl",
        "mcp-pdf-pro"
      ],
      "env": {
        "PYTHONUTF8": "1",
        
        // 🔥 【必填】请填入你的 API Key (智谱/OpenAI/DeepSeek 等)
        "MCP_API_KEY": "sk-xxxxxxxxxxxxxxxxxxxxxxxx",

        // 🌍 【选填】API 地址 (默认为智谱 GLM-4V,如需改用其他模型请修改)
        "MCP_BASE_URL": "[https://open.bigmodel.cn/api/paas/v4/](https://open.bigmodel.cn/api/paas/v4/)",
        "MCP_MODEL_NAME": "glm-4v"
      },
      "type": "stdio"
    }
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_pdf_pro-0.1.0.tar.gz (4.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_pdf_pro-0.1.0-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

Details for the file mcp_pdf_pro-0.1.0.tar.gz.

File metadata

  • Download URL: mcp_pdf_pro-0.1.0.tar.gz
  • Upload date:
  • Size: 4.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Hatch/1.16.2 cpython/3.12.0 HTTPX/0.28.1

File hashes

Hashes for mcp_pdf_pro-0.1.0.tar.gz
Algorithm Hash digest
SHA256 57a8bd75b43bd5a34948ad269100e62c63cc0b775f0345a07dd3fd7ea953d0e6
MD5 059dd4517f390a21be24fb61d6bcefa8
BLAKE2b-256 45cd3e4528d75c21490eac2cc6fcf8bcb961a0f7ebfad5c94eebbab726a3853c

See more details on using hashes here.

File details

Details for the file mcp_pdf_pro-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: mcp_pdf_pro-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 4.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Hatch/1.16.2 cpython/3.12.0 HTTPX/0.28.1

File hashes

Hashes for mcp_pdf_pro-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 067792b22be58ae2c4f3656c1f9cd5471f2bcd7a5294ecd289c72e87d68b9791
MD5 3c4d81dfc131202711e9129ebc0dd533
BLAKE2b-256 a71af3e05b2bfe3ddcd3816260e6b09572d2146b7603b3be84240f5ce3624035

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page