thedaviddias/Front-End-Checklist
Front-End Checklist is an open-source quality system for modern web development, offering comprehensive best practices for humans and AI agents.
Awesome AI Agents › MCP Server Framework
apify/apify-mcp-server
The Apify MCP Server makes any Actor from the Apify Store usable as a tool by an AI assistant through the Model Context Protocol. Actors are ready-made scrapers, crawlers and automation programs, so an agent connected to the server can extract data from social networks, search engine result pages, maps, e-commerce sites and arbitrary websites without bespoke integration code. The README gives concrete examples such as the Facebook Posts Scraper for pulling posts across multiple pages and profiles, the Google Maps Email Extractor for contact details, the Google Search Results Scraper for SERPs, the Instagram Scraper for posts, profiles, places, photos and comments, and the RAG Web Browser, which searches the web, scrapes the top results and returns their content. There are two ways to run it. The hosted endpoint at mcp.apify.com uses streamable HTTP and supports OAuth, so clients such as Claude.ai or Visual Studio Code can connect with only a URL, or with an Authorization bearer header carrying an Apify API token; the hosted server also carries newer features such as output schema inference for structured Actor results. Alternatively the server runs locally over standard input and output via npx @apify/actors-mcp-server with an APIFY_TOKEN environment variable, which suits command-line and desktop clients. The legacy server-sent-events endpoint has been removed in favour of streamable HTTP. The server also supports agentic payments, either through an AGI token that can run any Actor, or per request via direct x402 for pay-per-event Actors, or via Skyfire. It is written in TypeScript, published on npm, and exposes tools, resources and prompts along with telemetry. Because client support for dynamic tool discovery varies, the documentation lists tested clients including Claude Desktop, Claude Code, Cursor and VS Code.
https://github.com/apify/apify-mcp-server
Also in MCP Server Framework
PrefectHQ/fastmcp
FastMCP offers a Pythonic framework for building Model Context Protocol (MCP) servers and clients, facilitating structured communication for AI agents and models.
pascalorg/editor
Local-first 3D building editor built with React Three Fiber and WebGPU that exposes an MCP service so AI agents can create and edit 3D scenes.
trycua/cua
c/ua is a high-performance framework that enables AI agents to control full macOS and Linux operating systems within secure, lightweight virtual containers on Apple Silicon Macs, supporting complex autonomous workflows and LLM integration.
nukeop/nuclear
Nuclear is a free, open-source, ad-free music player for Windows, macOS, and Linux, featuring streaming from various sources, playlist management, a powerful plugin system, and integration with AI ...
googleapis/mcp-toolbox
MCP Toolbox for Databases is an open-source server that connects AI agents and applications to enterprise databases using the Model Context Protocol (MCP).
grab/cursor-talk-to-figma-mcp
Cursor Talk to Figma MCP is an integration that enables Cursor AI to communicate with Figma programmatically for reading and modifying designs, automating and enhancing the design workflow.
Helicone/helicone
Helicone is an open-source LLM observability platform that enables developers to monitor, evaluate, and experiment with large language model applications through easy integration and comprehensive tools.