Custom MCP 服务器 | PlugMCP
跳到正文
What is MCP?
Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect with external data sources and tools. MCP servers act as bridges between AI models and various services, allowing for enhanced capabilities like real-time data access, API integrations, and custom tool execution.
MCP server for scraping LinkedIn, Facebook, Instagram profiles and Google search.
把任意工具接入任意智能体。面向非开发者的 MCP 服务器目录;网关承载流量,n8n 承载应用。
产品
目录
开发者
公司
Features This server exposes the following tools for an AI assistant to use:
LinkedIn Profile Scraping : Extract personal and company profile data
Facebook Profile Scraping : Fetch public profile information
Instagram Profile Scraping : Get profile data and basic information
Google Search : Perform web searches using Google Serper API
Installation
Step 1: Adding MCP to your Python project We recommend using uv to manage your Python projects.
If you haven't created a uv-managed project yet, create one:
uv init custom-mcp-server
cd custom-mcp-server
Step 2: Install MCP Dependencies Then add MCP to your project dependencies:
This will auto-generate files and folders similar to the project structure mentioned below, also create a .env file to securely store the API keys.
Step 3: Add Project Code In the files generated look for main.py and copy paste the code given in main.py (repo).
Step 4: Install Additional Dependencies uv add httpx python-dotenv fastmcp
Environment Configuration
Step 1: API Keys Setup
RapidAPI Key :
Sign up at RapidAPI
Subscribe to the following APIs (Most Important):
Fresh LinkedIn Profile Data
Facebook Scraper3
Instagram Scraper Stable API
Google Serper API Key :
Sign up at Serper.dev
Get your API key from the dashboard
Step 2: Environment Variables Create .env file in your project root with the following variables:
RAPIDAPI_KEY=your_rapidapi_key_here
SERPER_API_KEY=your_serper_api_key_here
Usage
Running with Claude Desktop
Step 1: Install the Server You can install this server in Claude Desktop and interact with it right away by running:
uv run mcp install main.py
Step 2: Verify Installation Later, go to Claude AI (desktop version) and you will see changes in the platform similar to the screenshot shown .
Step 3: Start Using the Tools Paste the URLs of required platform and ask the AI to provide information of the mentioned URLs.
Example Usage Please scrape this LinkedIn profile: https://linkedin.com/in/example-profile
Get company information for: https://linkedin.com/company/example-company
Troubleshooting If the MCP tools don't appear in Claude Desktop:
Step 1: End Claude Processes
Windows: Open Task Manager (Ctrl+Shift+Esc)
Mac: Open Activity Monitor
End all Claude-related processes
Step 2: Reinstall the Server uv run mcp install main.py
Step 3: Restart Claude Desktop Paste the URLs of required platform and ask the AI to provide information of the mentioned URLs.
Testing with MCP Inspector Alternatively, you can test it with the MCP Inspector:
Project Structure custom-mcp-server/
├── __pycache__/ # Python bytecode cache (auto-generated)
├── .venv/ # Virtual environment directory
├── .env # Environment variables (API keys)
├── .python-version # Python version specification
├── main.py # Main MCP server implementation
├── pyproject.toml # Project configuration and dependencies
├── README.md # Project documentation
└── uv.lock # UV lock file for reproducible builds
Response Format All tools return JSON-formatted strings containing the scraped data. Example response structure:
{
"success": true,
"data": {
"profile": {
"name": "John Doe",
"title": "Software Engineer",
"location": "San Francisco, CA",
"bio": "Passionate about technology..."
}
},
"timestamp": "2024-01-15T10:30:00Z"
}
But using these tools via Claudes makes it readable.
Contributing
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
In case of any queries, please leave a message or contact me via the email provided in my profile.
SparkForge Access a versatile collection of tools for media generation, web scraping, and cryptocurrency research. Convert between data formats, summarize long documents, and extract text from images or PDFs wit Scrapling MCP Server Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported. Scrapling 🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and trick Fetch Fetch a web page and return it as clean markdown for the agent, in chunks for long pages. The reference server from the Model Context Protocol project. Obscura The headless browser for AI agents and web scraping Douyin TikTok Download API 🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API,支持 AI agent 通过 MCP 调用与离线语音转文字,Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI age Web Scout Search the web and extract clean, readable text from webpages. Process multiple URLs at once to speed up research with reliable throttling and error handling. Quickly compile sources and summaries for Apify The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automa Apify MCP Server Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡ Skill Seekers Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection SeleniumBase 📊 Python APIs for Web Automation, Testing, and Scraping. CDP Mode launches a stealth browser that bypasses bot-detection/CAPTCHAs. Adds stealth to Playwright and has an MCP server for AI agents. Mobile Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices) Web scraping MCP 服务器 最佳 Web scraping MCP 服务器
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
如何安装 Custom? 在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
Custom 需要 API 密钥吗? 此记录未列出必需的环境变量。
Custom 使用哪种传输方式? Custom 通过 stdio 在本地运行。
Custom 上次检查是什么时候? 上次检查时间:2026-10-27。 MCP server for scraping LinkedIn, Facebook, Instagram profiles and Google search.
工具
0 / 10