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
MicrosoftDocs/mcp
This repository documents the Microsoft Learn MCP Server, a hosted remote endpoint that any tool speaking the Model Context Protocol can connect to over Streamable HTTP. The stated purpose is to keep coding assistants such as Claude, Cursor, Copilot and Codex from inventing APIs by grounding their answers in first-party Microsoft documentation rather than stale training data or arbitrary web pages. The server needs no API key, login or sign-up, and clients are configured by pointing them at the documented HTTP endpoint; the URL is intended for MCP clients only and returns an error if opened in a browser. Three tools are exposed: microsoft_docs_search, which runs a semantic search over official Microsoft technical documentation for a query string; microsoft_docs_fetch, which retrieves a documentation page and converts it to markdown; and microsoft_code_sample_search, which finds official Microsoft and Azure code snippets with an optional programming language filter. Experimental features include an OpenAI-compatible endpoint that follows the OpenAI MCP specification for Deep Research models, and a maxTokenBudget query parameter that caps token usage by truncating search tool responses to a chosen budget. The repository also hosts a preview command line tool published as an npm package, which exposes the same documentation search, page fetch and code sample lookup from a terminal without an MCP client and can emit structured JSON for scripting. Alongside the server it ships three agent skills that instruct agents on when and how to use the tools: one for concepts, tutorials and configuration guides, one for API lookups and error fixing, and a meta-skill that generates custom skills for other Microsoft technologies. The skills and the server are bundled as a plugin installable in Claude Code and the GitHub Copilot CLI.
https://github.com/MicrosoftDocs/mcp
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.