MCP Web Search
Provides 19 tools for web search, content fetching, and extraction, including DuckDuckGo search, YouTube transcripts, and webpage screenshots.
README
MCP Web Search Server
A powerful Model Context Protocol (MCP) server that provides AI agents with internet search and web content capabilities.
Features
This MCP server provides 19 tools for web interaction:
🔍 Search Tools
search_web- DuckDuckGo text searchsearch_news- Latest news searchsearch_images- Image searchsearch_youtube- YouTube video searchsearch_wikipedia- Wikipedia article searchsearch_maps- Places/maps searchbatch_search- Multiple queries in one call
🌐 Web Fetching Tools
fetch_webpage- Fetch static HTML pagesfetch_webpage_js- Fetch JavaScript-rendered pages (Playwright)fetch_as_markdown- Convert webpage to clean Markdown (LLM-friendly)crawl_website- Multi-page website crawling
📄 Content Extraction Tools
get_youtube_transcript- Extract YouTube video transcriptsread_pdf_url- Read PDF documents from URLsextract_links- Extract all links from a pageget_page_metadata- Get SEO/meta informationtake_screenshot- Capture webpage screenshots
🛠️ Utility Tools
get_weather- Weather lookuptranslate_text- Text translationclear_cache- Clear cached results
Installation
Prerequisites
- Python 3.10+
- pip
Setup
- Clone the repository:
git clone https://github.com/YOUR_USERNAME/MCP-Web-Search.git
cd MCP-Web-Search
- Create and activate virtual environment:
python -m venv .venv
# Windows
.venv\Scripts\activate
# macOS/Linux
source .venv/bin/activate
- Install dependencies:
pip install fastmcp ddgs httpx lxml playwright markdownify youtube-transcript-api pymupdf
- Install Playwright browser:
python -m playwright install chromium
Configuration
VS Code (GitHub Copilot)
Add to your settings.json or create .vscode/mcp.json:
{
"servers": {
"internet-search": {
"type": "stdio",
"command": "/path/to/.venv/Scripts/python.exe",
"args": ["/path/to/search_server.py"]
}
}
}
Google Antigravity IDE
Add to your mcp_config.json:
{
"mcpServers": {
"internet-search": {
"command": "/path/to/.venv/Scripts/python.exe",
"args": ["/path/to/search_server.py"],
"env": {}
}
}
}
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"internet-search": {
"command": "/path/to/.venv/Scripts/python.exe",
"args": ["/path/to/search_server.py"]
}
}
}
Usage Examples
Once configured, you can ask your AI assistant:
- "Search the web for latest Python 3.13 features"
- "Fetch the content from python.org as markdown"
- "Get the transcript of this YouTube video: [URL]"
- "Read this PDF document: [URL]"
- "Take a screenshot of example.com"
- "What's the weather in New York?"
Testing
Run the server in test mode:
python search_server.py --test "your search query"
License
MIT License
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.