MCP servers
38 servers that let your AI assistant read data and take actions in the tools you use.
Web-To-MCP
Web-to-MCP
Web-to-MCP lets you capture any real UI component from a live website and pull its exact details into your AI coding assistant. Click the Chrome extension, select an element, and you’ll get a reference ID. Paste that ID in Cursor or Claude, and your MCP server returns the component’s HTML, CSS, typography, colors, spacing, and layout context. What this really means is you stop guessing from screenshots and start from the source of truth. How it works 1. Open the extension and pick any element on a page. 2. Receive a reference ID for that capture. 3. In your IDE chat, call the MCP tool with the ID to fetch the spec and code. What you get Exact DOM structure plus consolidated CSS. Computed styles for sizing, spacing, fonts, and colors. Small preview image for quick visual check. Clean output you can use in React, Vue, Angular, or plain HTML/CSS. Why it’s useful Designers grab examples fast. Developers get accurate code. The handoff shrinks from trial-and-error to minutes, so teams ship UI that matches what they saw on the web.
mcps
walkingshamrock
mcps is a Unix filter for selecting MCP servers from JSON configurations.
infio-copilot
infiolab
A Cursor-inspired AI assistant for Obsidian that offers smart autocomplete and interactive chat with your selected notes
MCP tool for browser inspection, element selection, and responsive testing
mcp-amazon-server
airskywater
README This is a server based on the Model Context Protocol (MCP) for evaluating the costs and profits of selling products on Amazon, helping Amazon sellers to select products more efficiently.
Crawl4AI-MCP
Dabliou
Crawl4AI-MCP: A powerful web crawling and content analysis server that combines targeted web scraping with Claude AI processing. Extract insights from specific websites with customizable depth, content selection, and AI analysis capabilities.
mcp-demo
minton1024
An intelligent Agent based on MCP protocol for tool selection and request handling.
chatter
sakalys
A hosted, model-agnostic (llm-agnostic) chat client (hosted on https://moopoint.io). Users can select their preferred LLM provider and models and use their own API keys. The platform also supports MCP (Model Context Protocol).
GemForge (Google Gemini)
pv-bhat
Provides a specialized server that connects to Google's Gemini models with optimized tools for search, reasoning, code analysis, and file operations, automatically selecting the best model based on task requirements.
Resemble
obaid
Provides a bridge to the Resemble AI text-to-speech API, enabling dynamic voice generation for multimedia content through flexible server transport methods and voice model selection.
Scrappey
pim97
Bridges AI models with Scrappey's web automation platform, enabling browser session management, HTTP requests, and complex browser actions while automatically handling anti-bot protections and enhancing web content with CSS selectors for interactive elements.
TwoSplit
lazerthings
Leverages multiple Claude instances to compare and combine responses, delivering optimized answers by selecting the best output or merging insights from parallel AI processing.
Krep
bmorphism
Provides a high-performance string search utility that automatically selects optimal algorithms and leverages hardware acceleration for significantly faster pattern matching than traditional tools like grep.
smart-mcp-server
reconsumeralization
Smart MCP Server intelligently selects tools based on user context and history.
mcp-registry
cccntu
MCP Registry simplifies MCP server configuration management and selective exposure.
mcp-web-content-pick
kilicmu
A tool for extracting structured content from web pages, featuring customizable selectors and crawling options.
LangChain4j-Springboot
melon1010
Combine LangChain4j with Spring Boot to Build an Intelligent AI Application This project integrates the GitHub API, web scraping, Ollama local AI models, and features the MCP (Model Configuration Protocol) intelligent tool selection functionality.