MCP Web Search
Provides web search, news search, image search, and maps search capabilities using DuckDuckGo.
Provides Wikipedia article search.
Provides YouTube video search and transcript extraction.
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., "@MCP Web Searchsearch the web for latest AI news"
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.
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
Related MCP server: MCP Web Tools Server
Installation
Prerequisites
Python 3.10+
pip
Setup
Clone the repository:
git clone https://github.com/YOUR_USERNAME/MCP-Web-Search.git
cd MCP-Web-SearchCreate and activate virtual environment:
python -m venv .venv
# Windows
.venv\Scripts\activate
# macOS/Linux
source .venv/bin/activateInstall dependencies:
pip install fastmcp ddgs httpx lxml playwright markdownify youtube-transcript-api pymupdfInstall Playwright browser:
python -m playwright install chromiumConfiguration
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.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- 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/jsitla/MCP-Web-Search'
If you have feedback or need assistance with the MCP directory API, please join our Discord server