MCP Web Search Server

A Model Context Protocol (MCP) server that enables Amazon Q to search the web and fetch content from URLs, extending its capabilities beyond its built-in knowledge.

Prerequisites

• Python 3.11+
• Amazon Q CLI installed
• Git

Quick Installation

One-Command Setup

git clone <repository-url>
cd mcp-web-search
./install.sh

That's it! The MCP server is now available in Amazon Q.

Manual Installation

If you prefer to install step by step:

1. Clone and setup

git clone <repository-url>
cd mcp-web-search

2. Install dependencies

# Using uv (recommended)
uv venv
source .venv/bin/activate
uv sync

# Or using pip
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

3. Add to Amazon Q

chmod +x run_server.sh
q mcp add --name web-search --command "$(pwd)/run_server.sh"

Tools

web_search

Search the web using Google Search API.

Parameters:

• query (string, required): Search query
• max_results (integer, optional): Maximum number of results (default: 10)

Returns: Structured JSON with search results including titles, URLs, and snippets

web_fetch

Fetch and extract content from a web page with intelligent filtering.

Parameters:

• url (string, required): URL to fetch
• format (string, optional): Output format - "markdown" or "text" (default: "markdown")

Returns: Cleaned and filtered content (limited to 8000 characters)