Web Search MCP Server

If you want an AI assistant working directly with Web Search MCP, the web search mcp mcp server is the bridge. A Model Context Protocol (MCP) server that provides web search functionality by scraping Google, DuckDuckGo, and Bing search results through a headless browser.

What Web Search MCP does

A Model Context Protocol (MCP) server that provides web search functionality by scraping Google, DuckDuckGo, and Bing search results through a headless browser.

Key capabilities

• Multi-Engine Search — Searches Google, DuckDuckGo, and Bing with automatic fallback when an engine is blocked or returns nothing
• Structured Results — Titles, URLs, domains, snippets, and rankings — with redirect URLs unwrapped to their real destinations
• Web Page Content — Fetch and extract text content from any webpage
• Pluggable Browser Backends — Selenium + headless Chrome (default) or the lightweight Obscura headless browser, selected via an environment variable
• MCP Compatible — Fully compatible with Claude Desktop and other MCP clients

Tools it exposes

Once connected, the assistant can call these 4 tools directly:

• search_web — Search the web across multiple engines (Google → DuckDuckGo → Bing) with automatic fallback and return structured results
• get_webpage_content — The get_webpage_content tool exposed by this server
• get_search_engine_status — Report the active browser backend and the availability of each search engine
• reset_search_engines — Clear the list of engines marked as blocked during the session (useful if an engine recovers)

Installing the web search mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Requirements

• Python 3.10+ - A browser backend: Chrome (Selenium) or the Obscura binary - Internet connection

Where it fits

Browser automation servers are the ones people reach for when a site has no API — the assistant drives a real page instead of guessing at endpoints. Web Search MCP sits in that group, and the shape of its toolset — search_web, get_webpage_content, get_search_engine_status among others — tells you what it is really for. Worth comparing against the other browser automation servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

• This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
• Maintained by pranavms13, written in Python.
• MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the web search mcp mcp server actually does with your data.
• Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.