An MCP server based on browser - use, enabling AI agents to control web browsers for automated operations.

This is a curated list of Web3 Model Context Protocol (MCP) servers, covering multiple categories such as chain interaction, trading, DeFi, market data, tools, and social. MCP is an open protocol that standardizes how applications provide context to LLMs, similar to the USB - C port for AI applications. DeMCP is the first decentralized MCP network, focusing on providing self - developed and open - source MCP services for agents, supporting cryptocurrency payments, and redefining the security and reliability of MCP by combining TEE and blockchain registries.

The AI Infrastructure Agent is an intelligent system that allows users to manage AWS cloud resources through natural language commands. It uses AI models to convert user requirements into executable AWS operations and provides web dashboards, state management, and security protection functions.

The Crawl4AI RAG MCP Server is an AI agent service integrating web crawler and RAG functions, supporting smart URL detection, recursive crawling, parallel processing, and vector search. It aims to provide powerful knowledge acquisition and retrieval capabilities for AI coding assistants.

Pipelock is an open-source AI agent firewall that provides security protection with zero runtime dependencies through a single binary file. It adopts an architecture with separated capabilities and deploys a nine-layer scanning pipeline between the agent and the Internet to prevent secret leakage, prompt injection, and malicious tool calls. It supports multiple proxy modes (Fetch proxy, forward proxy, WebSocket proxy) and MCP proxy, and provides functions such as an emergency stop switch, audit logs, and SIEM integration.

An MCP server implemented for the RAG Web Browser Actor, supporting AI agents to perform web searches and content extraction.

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.

The VibeCheck Web testing tool is an AI-driven web testing agent designed to simplify the web testing process for developers. It integrates with AI programming assistants through the MCP protocol, supporting automated test recording, execution, and discovery, and helping developers quickly identify and fix code issues.

A lightweight MCP server based on Python that interacts with local ComfyUI via WebSocket to enable programmatic image generation by AI agents.

MCPez is a microservice command proxy management platform that unifies the management and standardizes the interfaces of backend services through a web interface, simplifying the integration of AI agents and tools.

Deep Research is an agent - based tool that provides web search and advanced research functions, supports PDF analysis, image description, and YouTube transcription extraction, and can run as an MCP server.

Snowfort Circuit MCP is a comprehensive Model Context Protocol server suite that provides web and Electron desktop application automation capabilities for AI coding agents, with features such as AI - optimized snapshots, intelligent screenshot compression, and multi - session management.

The VibeCheck Web testing tool is an AI-driven web testing agent integrated into AI programming assistants (such as GitHub Copilot, Cursor, etc.) through the MCP protocol to achieve automated test recording, execution, and discovery. It uses Playwright to control the browser, supports generating test scripts through natural language description, executes regression tests, and automatically discovers potential test steps, improving development efficiency and test accuracy.

An OpenAI agent server based on the MCP protocol, providing various professional agents (such as web search, file search, and computer operation) and a multi-agent coordinator, which can interact with clients (such as the Claude desktop application) through the MCP protocol.

An autonomous AI research agent based on the MCP protocol, capable of completing the full research process such as web search, knowledge base retrieval, code writing, chart generation, and report writing through a single prompt.

Webflow MCP is a Node.js-based server that implements the Model Context Protocol (MCP), allowing AI agents to interact with the Webflow API through the Webflow JavaScript SDK.

An MCP server based on Selenium WebDriver that allows AI agents to control browser sessions through the MCP protocol, enabling web automation operations such as navigation, element searching, and form filling.

The You.com DX Toolkit is an open-source AI development toolkit that includes npm packages, plugins, and skills, and can work in conjunction with more than 20 AI programming assistants such as Claude Code and Cursor. It provides tools such as the MCP server, Vercel AI SDK plugin, and Teams.ai integration, supporting real-time web search, AI agents, and content extraction functions.

This project is a collection of OpenRewrite recipes for automatically converting Spring Web REST APIs into Spring AI's Model Context Protocol (MCP) server tools, enabling the migration of traditional APIs to tools accessible by AI agents.

The Nodit MCP Server is a middleware that connects AI agents and developers to multi - chain structured blockchain data, providing simplified Web3 data access through the standardized Model Context Protocol.

Webcam MCP is an MCP server that provides webcam access for LLM agents, supporting photo taking and video recording, enabling AI agents to independently observe and interact with the physical environment.

This project provides two MCP server implementations that connect Claude Desktop to Azure search capabilities, supporting searches for document and web content through the Azure AI Agent Service (recommended) or direct Azure AI Search integration.

Mitto is a modern AI programming assistant management platform that supports connecting multiple ACP - compatible AI coding agents, providing a native macOS application, a web interface, and a CLI for cross - device session management and real - time collaboration.

Scrapi AI's MCP server can convert web page URLs into clean Markdown/text formats for AI agents to read and analyze web page content, supporting JavaScript rendering and batch processing.

Gemini DeepSearch MCP is an automated research agent that uses the Google Gemini model and Google Search for in-depth multi-step web research and generates high-quality, referenced answers.

Fetch Browser is a powerful headless browser MCP server designed for AI agents, which can obtain web page content and perform Google searches without API keys. It supports multiple content format conversions and intelligent error handling.

An MCP server integrating the Agent.ai API, providing functions for web page text extraction, web page screenshot capture, and YouTube subtitle acquisition, supporting dynamic function loading and a cache mechanism.

Search Stack is a web search and scraping middleware layer specifically designed for AI Agents, providing a unified API for multi-engine search, anti-crawler rendering, Cookie management, and main content extraction. It aims to solve problems such as quota limitations, anti-crawler interception, and lack of login states that AI encounters when accessing web pages.

MCP Server Notifier is a lightweight notification service integrated with the Model Context Protocol (MCP), which can send Webhook notifications when an AI agent completes a task. It supports multiple Webhook providers (e.g., Discord, Slack, Teams, etc.), provides features such as image support, multi - project management, and custom messages, and is easy to integrate with AI tools (e.g., Cursor).

A webpage summary agent tool based on mcp-agent and Qwen, which can run in the Windows environment. It can be used by creating a virtual environment with uv and configuring the API key.

TPC Server is a backend service for recording and tracking the thought processes of AI agents or projects. It manages the associated data of thoughts, plans, and changes through structured logging and provides Web interface and API access.

MCPez is a microservice command proxy management platform that unifies the management and standardizes the backend service interfaces through a web interface, simplifying the integration and deployment of applications such as AI agents.

A Puppeteer - based webpage screenshot MCP service that supports full - page screenshots, element screenshots, multiple image formats, custom options, and authentication session management. It can be used for AI agents to visually verify web applications.

An intelligent research agent tool based on HuggingFace smolagents, providing advanced research functions such as web search and document analysis

The AgentQL MCP Server is a model context protocol server integrating AgentQL's data extraction capabilities, supporting the extraction of structured data from web pages.

An MCP server based on the crawl4ai library, providing web page crawling and intelligent content extraction functions, supporting AI agents to interact with web pages through natural language instructions.

persistproc is a shared process layer tool designed for multi - agent development workflows. Through the MCP server and command - line tool, it allows agents and human users to view and control long - running processes (such as web servers). Its aim is to reduce copy - paste operations when coding with AI, support multi - agent collaboration, and remain tool - independent.

The MCP Browser is a headless browser interface based on Playwright, supporting web UI interaction and WebSocket real-time communication. It is designed for AI agent and MCP protocol integration.

mcp - searxng is an MCP server example designed for AI agents, which implements the external information search function through the open - source meta - search engine SearXNG. The project demonstrates how to integrate SearXNG and Microsoft's markdownify tool to convert web page content into Markdown - formatted text and communicate with MCP clients via the SSE protocol.

The Webvizio MCP Server is a TypeScript - based model context protocol server that provides secure and structured access to the Webvizio API. It can automatically convert website feedback and error reports into executable development tasks for AI coding agents to process.