# Web search

The Tavily MCP Server is an open-source tool based on the Model Context Protocol (MCP) that provides real-time web search and data extraction capabilities for AI systems such as Claude. It supports seamless integration with multiple MCP clients (such as Cline, Cursor, and Claude Desktop), enabling AI assistants to access Tavily's advanced search and content extraction functions.

An MCP server implemented with the Kagi search API based on Node.js, providing web search functionality for AI assistants, supporting parallel queries and formatted results.

An MCP server implementation integrating the Brave Search API, providing web and local search functions, supporting pagination, filtering, and smart fallback mechanisms.

An MCP server based on SearxNG that provides privacy-protective web search functions for AI assistants, supporting multiple integration methods and transmission protocols.

An MCP server based on DuckDuckGo, providing web search and content crawling functions, with features such as rate limiting and LLM-friendly output.

This project provides two implementations of the MCP server, connecting Claude Desktop with Azure search capabilities, supporting document search and web search. You can choose to use the Azure AI Agent service or directly integrate Azure AI Search.

A model context service extension that provides Brave search for the Zed AI assistant, supporting web and local search commands.

A locally run RAG - style Model Context Protocol (MCP) server for web search. It can provide the latest web information retrieval function for models such as Claude without using an API.

The Crawleo MCP Server provides real-time web search and content crawling functions for AI assistants. It is integrated through the Model Context Protocol, supporting multi-format output and deep content extraction.

An MCP server based on the Synthetic API that provides web search tools for MCP-compatible applications such as Claude.

Google Researcher MCP Server is a service that provides professional research tools for AI assistants, supporting Google search, web scraping, academic paper and patent queries, etc. It can be integrated into AI applications such as Claude through the MCP protocol.

The MCP Edge Search Server is a Python service that provides web search and content extraction functions for MCP clients (such as Claude Desktop), supporting Bing search and web text cleaning.

An MCP server implementation integrating the Brave Search API, providing web search and local search functions.

A Tavily search and content extraction MCP server implemented in Rust, providing web search and URL content extraction functions for AI proxy systems through a standardized protocol.

A simple MCP server based on Perplexity AI, providing web search functionality

This project implements an MCP protocol server that provides a web search tool based on OpenRouter and can generate concise and real - time answers.

Provide MCP search services based on SearxNG

Parallel Search MCP is a tool that allows the use of parallel search APIs in MCP-compatible LLM clients, suitable for daily small-scale web search tasks

This is an MCP server for the Synthetic Search API designed for personal use. It can run locally through OpenCode configuration and provides web search functionality.

SearXNG MCP is a model context protocol server based on the SearXNG privacy-protecting metasearch engine, providing web search functionality for AI assistants. It supports zero-configuration use of public instances or connection to private instances, with features such as customizable search parameters, multi-search engine support, and privacy-first.

A powerful MCP server that provides web search and similar content lookup functions, designed specifically for Claude Desktop.

WebSearch-MCP is a service that implements the Model Context Protocol (MCP). It provides web search capabilities by integrating the WebSearch Crawler API and supports multiple AI clients to obtain web information in real-time.

An MCP server based on the Google Custom Search API, providing web search and content extraction functions.

This is a project based on the MCP protocol that integrates Zhipu AI and Tencent Map API, providing functions such as weather query, geocoding, and web search, and supporting two interaction methods: command line and web interface.

An MCP server implementation that integrates the Google Custom Search JSON API, providing web search functionality, supporting advanced filtering and returning structured results.

An MCP protocol server based on the Google Custom Search API, providing standardized web search capabilities for language models.

An MCP server based on Puppeteer that provides Google web search functionality and returns structured JSON results.

An MCP service that combines DuckDuckGo search, web content extraction, and screenshot functions, supporting programmatic access to online content.

An MCP server based on the Perplexity API, providing web search tools.

A modern MCP server based on the FastMCP framework, providing URL text fetching, web link extraction, and Brave search functions, supporting MCP-compatible clients such as LM Studio.