py-mcp-full
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@py-mcp-fullanalyze website structure for https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
py-mcp-full
PY Spider Development Full Toolset — MacCMS Video Site Analysis + Intelligent Source Code Generation + Selector Debugging + Play Link Debugging + Interface Testing + Code Standard Evaluation + Full File Operations
Based on the MCP (Model Context Protocol) protocol, it provides 18 professional tools for AI programming assistants, covering the entire workflow of video spider development.
✨ Features
🔍 Deep Website Structure Analysis — Automatically identifies MacCMS v8/v10/Collection API/non-standard architectures
🤖 Intelligent Source Code Generation — One-click generation of T3/T4 spider sources based on analysis results
🎯 Selector Debugging — Real-time verification of XPath/CSS selector matching results
🎬 Play Link Debugging — Recursive parsing of m3u8/mp4 direct links, supporting v8/v10 JS variable extraction
🧪 Interface Testing — Automated testing of five major interfaces (home/category/detail/search/play)
📋 Standard Evaluation — 12-item weighted check for spider source code standards
📁 Full File Operations — read/write/delete/mkdir/move/copy/info/cwd
🚀 Quick Start
Installation
git clone https://github.com/sunniu-hjdhnx/py-mcp-full.git
cd py-mcp-full
npm installConfigure MCP Client
Add to the configuration of MCP clients such as Claude Desktop / Cursor / Cherry Studio:
{
"mcpServers": {
"py_mcp_full": {
"command": "node",
"args": ["/path/to/py-mcp-full/index.js"],
"env": {
"ROOT": "/path/to/your/spider/project"
}
}
}
}The
ROOTenvironment variable specifies the root directory of the spider source project, and file operation tools are based on this path.
Lightweight Deployment (Optional)
Use esbuild to bundle into a single file, no node_modules required:
npm install -g esbuild
esbuild index.js --bundle --platform=node --format=cjs --target=node22 --outfile=dist/index.cjsConfiguration after bundling:
{
"mcpServers": {
"py_mcp_full": {
"command": "node",
"args": ["dist/index.cjs"],
"env": { "ROOT": "/path/to/your/spider/project" }
}
}
}🛠 Tool List (18)
Spider Development Tools (10)
Tool | Function | Required Parameters |
| Deeply analyze website structure and identify CMS type |
|
| Intelligently generate spider source code |
|
| Verify CSS selector matching results |
|
| Recursively debug play link extraction |
|
| Test the five major interfaces |
|
| Evaluate code standard compliance |
|
| Fetch page content |
|
| Replace file content |
|
| Search file content |
|
| List directory contents |
|
File Operation Tools (8)
Tool | Function | Required Parameters |
| Read file (supports segmentation) |
|
| Write file (overwrite/append) |
|
| Delete file or directory |
|
| Create directory (supports recursion) |
|
| Move/rename |
|
| Copy file |
|
| Get detailed file information |
|
| Get current working directory | — |
📖 Usage Workflow
① analyze_website(url="https://example.com")
→ 识别CMS类型,获取HTML结构参数
② debug_selector(url="...", selector="//div[contains(@class,'item')]")
→ 验证选择器是否正确
③ create_spider_source(url="...", mode="T4")
→ 生成完整爬虫源代码
④ test_interface(source_code="...", interface="all")
→ 测试五大接口是否正常
⑤ evaluate_source(source_code="...")
→ 检查规范符合度🏗 Project Structure
py-mcp-full/
├── index.js # 主程序(1409行)
├── package.json # 依赖配置
├── manifest.json # 工具 Schema 定义
└── 使用说明.md # 中文详细文档Repository Description
This README is only for explaining basic project information and repository boundaries, intended for technical learning and exchange, and does not contain usage guides, integration guides, or resource descriptions.
Acknowledgments
📄 License
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Official Octoparse MCP server for template discovery, cloud tasks, and structured data export.
SEO Intelligence MCP — 13 tools: keyword research, SERP, domain audits, competitors.
Hosted MCP with 91 agent tools: X, domains, SEO, Maps, Trends, Search, YouTube, TikTok, and more.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/GitSulay/py-mcp-full'
If you have feedback or need assistance with the MCP directory API, please join our Discord server