WebSearch-MCP logo

WebSearch-MCP

by mnhlt

WebSearch-MCP is a Model Context Protocol server that provides web search capabilities to AI assistants. It allows AI models to search the web in real-time, retrieving up-to-date information.

View on GitHub

Last updated: N/A

What is WebSearch-MCP?

WebSearch-MCP is a Model Context Protocol (MCP) server implementation that provides a web search capability over stdio transport. This server integrates with a WebSearch Crawler API to retrieve search results for AI models.

How to use WebSearch-MCP?

To use WebSearch-MCP, you need to install it via npm or Smithery, configure the API_URL for the WebSearch Crawler API, and integrate it with your AI client application by configuring the MCP server settings. The crawler service can be set up using Docker Compose.

Key features of WebSearch-MCP

  • Real-time web search for AI assistants

  • Integration with WebSearch Crawler API

  • Communication with AI assistants using Model Context Protocol

  • Configurable search parameters (query, number of results, language, region, etc.)

  • Support for excluding/including domains and terms in search results

Use cases of WebSearch-MCP

  • Providing up-to-date information to AI models

  • Enabling AI assistants to answer questions based on current web content

  • Augmenting AI model knowledge with real-time data

  • Integrating web search capabilities into AI-powered applications

  • Enhancing the context and relevance of AI-generated responses

FAQ from WebSearch-MCP

What is the default API_URL for the WebSearch Crawler API?

The default API_URL is http://localhost:3001.

How do I configure the maximum number of search results?

You can configure the maximum number of search results using the MAX_SEARCH_RESULT environment variable.

What is FlareSolverr used for?

FlareSolverr is used for bypassing Cloudflare protection on websites.

How do I test the WebSearch MCP server locally?

You can use the included test client by running the command: npm run test-client

What parameters can I use with the web_search tool?

You can use parameters such as query, numResults, language, region, excludeDomains, includeDomains, excludeTerms, and resultType.