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
statespace-tech/statespace
Statespace turns a directory of files and command-line tools into a self-describing data app that AI agents can discover and call. The premise stated in the README is that a model does not know your data but does understand Unix and filesystems, so the project exposes data through Markdown pages and constrained shell commands instead of a bespoke API. Running statespace init scaffolds an app in the current directory. Tools are declared in YAML front matter inside README.md or any other Markdown file: each entry is an argv array such as [grep] or [python, scripts/summarize.py], and an optional regex constrains what may be passed, for example limiting sqlite3 to statements matching a SELECT or EXPLAIN pattern. The body of the page holds the instructions the agent reads. statespace run serves the app over HTTP, where a GET returns a page and a POST executes one of the declared commands with a JSON body. statespace deploy publishes the app to the vendor cloud on a public subdomain, after which any agent can be pointed at the URL directly or wired up as an MCP server through the npx statespace-mcp bridge. Because pages are both the documentation and the interface, an app can be split across several files so an agent loads only the part it needs and spends fewer tokens. The regex constraints are the safety model: an agent can run only what the author explicitly allowed. Typical uses named in the README are database explorers, shared business rules and documentation for legacy APIs. The CLI is written in Rust, published on crates.io and installed with a shell script, and the project is MIT licensed. The GitHub repository is archived, and the same project is also reachable under its earlier name kruskal-labs/toolfront.
https://github.com/statespace-tech/statespace
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.