MCP Web Search Tool
A server for real-time web search using pluggable providers, powered by the Brave Search API.
MCP Web Search Tool
A powerful Model Context Protocol (MCP) server providing real-time web search capabilities through pluggable search providers. Currently integrated with the Brave Search API.

β¨ Features
- Real-Time Information Access: Enables AI assistants to retrieve up-to-date information from the web
- Pluggable Search Providers: Modular architecture allows for easy switching between different search engines
- Structured Output Format: Returns search results in a clean, consistent JSON format
- Smart Query Handling: Automatically categorizes queries and provides AI assistants with context-aware guidance
π Requirements
- Node.js: v16.x or newer
- npm: v7.x or newer
- Brave Search API Key: Required for accessing the Brave Search API
π Installation
-
Clone the Repository:
git clone https://github.com/gabrimatic/mcp-web-search-tool.git cd mcp-web-search-tool -
Install Dependencies:
npm install -
Configure Environment Variables: Create a
.envfile in the project root:BRAVE_API_KEY=your_api_key_here MAX_RESULTS=10 # Optional: Default is 10 REQUEST_TIMEOUT=10000 # Optional: Default is 10000ms -
Build the Project:
npm run build
π» Usage
Starting the Server
npm start
Testing the Server
node test-server.js
Integration with Claude Desktop App (optional)
One of the most exciting aspects of this project is its seamless integration with the Claude Desktop app. This integration allows users to ask Claude questions that require real-time information, and Claude will automatically use the web search tool to provide up-to-date answers.
Configuration
-
Create a
claude_desktop_config.jsonfile:{ "mcpServers": { "mcp-web-search": { "command": "node", "args": [ "/path/to/your/mcp-web-search-tool/build/index.js" ] } } } -
Launch Claude Desktop with your configuration file.
-
Ask Claude questions requiring real-time information, and it will automatically use the web search tool.
π₯ YouTube Video
Watch Claude in action using the MCP Web Search Tool for real-time AI browsing!
πΊ Claude + MCP Web Search β Live Demo
Example Queries:
- "What are analysts saying about the MVP race after tonightβs NBA games?"
- "What are the latest news about artificial intelligence?"
- "What's the weather like in New York today?"
- "How is the stock market performing right now?"
π οΈ Available Tools
Web Search
- Tool Name:
web_search - Description: Search the web for REAL-TIME information
- Necessarily For: Weather, current events, sports scores, stock market updates
- Parameters:
search_term(string): The search term to look upprovider(string, optional): Search provider (defaults to Brave)
Query Categories
The tool automatically categorizes queries into:
- Weather information
- Current events and news
- Sports scores and results
- Stock market and financial data
- Time-sensitive information
- General information seeking
π License
π¨βπ» Developer
Β© All rights reserved.
π Medium Article
Read more about the MCP Web Search Tool, its capabilities, and how it enhances AI-driven web search in our detailed Medium article: π Deep Dive into MCP Web Search Tool
β Support
Related Servers
YouTube MCP Server
Search YouTube videos, retrieve transcripts, and perform semantic search over video content.
Krep MCP Server
A high-performance string search server powered by the krep binary.
MCP NIF.PT
Query and analyze Portuguese companies using the NIF.PT public API. Supports search by NIF, company name, and city.
Gemini Search
Generates responses using the Gemini API and Google Search for up-to-date information.
Search Intent MCP
Analyzes user search keyword intent for SEO support using the AI Search Intent API.
IACR ePrint Archive
Search and retrieve cryptographic research papers from the IACR Cryptology ePrint Archive.
RSS3
Integrates the RSS3 API to query the Open Web.
Cryptocurrency Price
A service to query real-time cryptocurrency prices.
Google Maps
An MCP server for interacting with the Google Maps API, designed for Google Cloud Run.
Scholarly
Search for academic articles using scholarly vendors.