MCPs tagged with # web search

MCP ChatGPT Server runs as an MCP-compliant server, allowing users to access OpenAI's ChatGPT API seamlessly within Claude Desktop. It supports customizable model parameters, automated conversation state management, integrated web search for up-to-date information, and facilitates interactive discussions between Claude and ChatGPT. Users can configure model selection, temperature, token limits, and use their own OpenAI API keys.

• ⭐ 14
• MCP
• billster45/mcp-chatgpt-responses

MCP-searxng enables agentic systems to interface with web search engines via the SearXNG platform by implementing the Model Context Protocol. It supports both command-line and local server deployment, providing flexible integration options. Users can configure custom SearXNG server URLs and connect through clients like uvx or claude desktop. The tool simplifies access to structured web search within agentic workflows.

• ⭐ 107
• MCP
• SecretiveShell/MCP-searxng

Parallel Search MCP provides an interface to use the Parallel Search API seamlessly from any Model Context Protocol (MCP)-compatible language model client. It serves as a proxy server that connects requests to the search API, adding the necessary support for authentication and MCP compatibility. The tool is designed for everyday web search tasks and facilitates easy web integration for LLMs via standardized MCP infrastructure.

• ⭐ 3
• MCP
• parallel-web/search-mcp

mcp-local-rag is a local server implementing the Model Context Protocol (MCP) to provide retrieval-augmented generation (RAG) capabilities. It performs live web search, extracts relevant context using Google's MediaPipe Text Embedder, and supplies the information to large language models (LLMs) for enhanced, up-to-date responses. The tool is designed for easy local deployment, requiring no external APIs, and is compatible with multiple MCP clients. Security audits are available, and integration is demonstrated across several LLM platforms.

• ⭐ 89
• MCP
• nkapila6/mcp-local-rag

DuckDuckGo Search MCP Server provides web search capabilities through DuckDuckGo, with advanced content fetching and parsing tailored for large language models. It supports rate limiting, error handling, and delivers results in an LLM-friendly format. The server is designed for seamless integration with AI applications and tools like Claude Desktop, enabling enhanced web search and content extraction through the Model Context Protocol.

• ⭐ 637
• MCP
• nickclyde/duckduckgo-mcp-server

Implements a Model Context Protocol server that connects with the Brave Search API, enabling AI systems to perform comprehensive web, image, news, video, and local points of interest searches. Provides standardized MCP tools for various search types, each supporting advanced filtering parameters. Designed for easy integration in context-aware model interfaces such as Claude Code.

• ⭐ 86
• MCP
• mikechao/brave-search-mcp

SearXNG MCP Server implements the Model Context Protocol and integrates the SearXNG API to provide extensive web search functionalities. It features intelligent caching, advanced content extraction, and multiple configurable search parameters such as language, time range, and safe search levels. The server exposes tools for both web searching and URL content reading, supporting detailed output customization through input parameters. Designed for seamless MCP deployments, it supports Docker and NPX-based installation with rich configuration options.

• ⭐ 321
• MCP
• ihor-sokoliuk/mcp-searxng

OpenAI WebSearch MCP Server provides advanced web search functionality integrated with OpenAI's latest reasoning models, such as gpt-5 and o3-series. It features full compatibility with the Model Context Protocol, enabling easy integration into AI assistants that require up-to-date information and contextual awareness. Built with flexible configuration options, smart reasoning effort controls, and support for location-based search customization. Suitable for environments such as Claude Desktop, Cursor, and automated research workflows.

• ⭐ 75
• MCP
• ConechoAI/openai-websearch-mcp

Kagi-server MCP Server provides a TypeScript implementation of a Model Context Protocol (MCP) server that integrates with the Kagi Search API. It enables standardized tool access for performing web searches and plans for features like summarization, FastGPT integration, and enriched news results. Compatible with Claude Desktop and Smithery installations, it supports secure environment configuration and offers developer utilities such as automatic build and debugging via MCP Inspector.

• ⭐ 40
• MCP
• ac3xx/mcp-servers-kagi

Open-WebSearch MCP Server is a Model Context Protocol (MCP) compliant server offering web search functionalities using multiple search engines without the need for API keys or authentication. It provides structured search results with titles, URLs, and descriptions, and enables fetching of article content from supported sources such as CSDN and GitHub. The server supports extensive configuration through environment variables, including proxy settings and search engine customization. Designed for flexibility, it operates in both HTTP and stdio modes, making it suitable for integration into larger systems.

• ⭐ 463
• MCP
• Aas-ee/open-webSearch

WebSearch-MCP is a Model Context Protocol (MCP) server that enables real-time web search capabilities for AI assistants through the stdio transport. It connects with a web crawler API to retrieve up-to-date search results and serves these results to AI models like Claude. The solution offers straightforward configuration and seamless integration with various MCP clients, enhancing AI model access to current and relevant external information.

• ⭐ 19
• MCP
• mnhlt/WebSearch-MCP