# Web Search

ResearchMCP is a research tool that combines the Model Context Protocol (MCP) with multiple search engines, aiming to provide research capabilities similar to ChatGPT DeepResearch.

An MCP server based on the Kagi API, providing web search, content enhancement, and news acquisition functions.

A TypeScript-based MCP server that provides web search and content scraping functions through the Serper API and supports integration with Claude Desktop.

ReActMCP Web Search is an MCP server integrated with the Exa API, providing real-time web search functionality for AI assistants, supporting basic search and advanced filtering options, and returning results in Markdown format.

An MCP server implementation integrating the SearXNG API, providing web search functions and supporting features such as pagination, time filtering, language selection, and safe search.

WebSearch-MCP is a server implementation based on the Model Context Protocol (MCP), providing real-time web search capabilities for AI assistants.

An MCP server implementation integrating multiple search engines and web page scraping functions

A DuckDuckGo search plugin designed for Claude Code, providing functions such as web search, result detail acquisition, and related search suggestions, supporting advanced filtering and content exploration.

Bocha is a search engine designed specifically for AI, providing high-quality search services for nearly tens of billions of web pages and ecological content across the network, supporting structured data in multiple vertical fields such as weather, news, and encyclopedias, and suitable for various AI applications.

The Apify MCP Server is a service that implements the Model Context Protocol (MCP), allowing AI assistants to interact with various Actors on the Apify platform through SSE or Stdio to perform tasks such as data scraping and web search.

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.

An MCP server based on the Perplexity AI API, providing web search functionality for the Claude desktop client.

The Local MCP Tools Collection aims to simplify the integration of multi - functional tools for local large language models, supporting multiple MCP servers through a single virtual environment, including web search, Python sandbox, and long - term memory functions.

Zed extension that integrates exa-mcp-server to provide web search and content crawling functions

This project uses the SmolAgents library to build an AI assistant that integrates Brave Search and Crawl4ai's MCP server, capable of performing web searches and crawling functions.

An MCP server project for web search

An MCP server based on the Tavily API that provides real-time web search functionality for AI models and supports configuration of multiple search parameters.

o3 - search - mcp is an MCP server that supports using the OpenAI o3 model and its powerful web search function to help AI programming agents independently solve complex problems.

An MCPAgent interactive application based on Streamlit, with functions such as conversation memory, web search, and model selection, providing a modern and responsive user interface.

A powerful MCP server that provides web search and similar content search functions, supporting integration with Claude Desktop

An MCP server providing Marginalia search services

An MCP service for web search without an API key based on multiple search engines, supporting structured result return and article content retrieval

An MCP server that allows Claude Desktop to directly call the ChatGPT API, supporting custom parameters and web search functions.

WebSearch is an advanced web search and content extraction tool based on Python and the Firecrawl API, providing functions such as intelligent search, content scraping, and web crawling, and supporting MCP protocol integration.

DuckDuckGo Search MCP is a fast, privacy-friendly Model Context Protocol (MCP) server based on DuckDuckGo, providing web search and URL content extraction functions and being compatible with multiple AI providers.

A web search tool project based on DuckDuckGo, including an MCP server and client, which needs to be accessed through a browser interface

TOOL4LM is an MCP server that provides multi-tool support for local language models. It integrates functions such as web search, document reading, academic query, and calculator, and can enhance model capabilities without a default API key.

An MCP server implementation integrating the SearxNG API, providing web search functionality and supporting pagination control.

An MCP server that provides Perplexity API web search functionality for the Claude desktop application