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
SixHq/Overture
Overture addresses a common complaint about AI coding agents: they begin editing files immediately, so a misunderstood request is only discovered after hundreds of lines have been written. The tool installs as a Model Context Protocol server and works with any MCP-compatible agent, including Claude Code, Cursor, Cline, GitHub Copilot and Sixth AI, with per-client configuration snippets given in the README. When the agent starts planning, Overture intercepts that phase and opens a local web interface, by default on port 3031, that renders the plan as an interactive graph rather than a block of chat text. The graph makes explicit what plain text hides: which tasks depend on which others, where alternative approaches branch, what files, APIs or secrets each step needs, which steps carry risk, and how far execution has progressed. Users can pan, zoom and click through nodes, attach context such as files, keys or extra instructions to individual steps, and compare the advantages and disadvantages of competing approaches before choosing one. The agent does not write code until the plan is approved. Once execution begins, nodes light up as they complete, so the flowchart doubles as a progress view. A built-in MCP marketplace lets the user browse tools and attach them to specific nodes, scoping capabilities per step instead of granting them globally. Everything runs locally as an npm package, published as overture-mcp and installable through npx or a global install, and the project is MIT licensed with continuous integration on GitHub. It is aimed at developers who use coding agents on non-trivial tasks and want a review gate between the prompt and the diff.
https://github.com/SixHq/Overture
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).
apify/apify-mcp-server
Model Context Protocol server that exposes thousands of Apify Actors as tools, letting AI agents scrape social media, search engines, maps and e-commerce sites over hosted HTTP or local stdio.
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.