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
SylphxAI/pdf-reader-mcp
Citra, published from the pdf-reader-mcp repository as the npm package @sylphx/citra, is a PDF reading layer for AI agents. It runs as a stdio MCP server started with a single npx command, needing no Docker, API key or global install, and the same code is also available as a command line tool and as an SDK import. Registration snippets are provided for Claude Code, Claude Desktop, Cursor, VS Code, Codex and any other MCP client, and hosts that send server discovery before initialize are supported on stdio. The tool surface is deliberately small. read_pdf is the default path and returns markdown, tables, document structure, OCR output and citations. search_pdf finds pages and snippets before a deeper read. pdf_evidence handles crops, renders, inspection and other focused evidence operations. The stated design goal is that an agent should be able to defend an answer rather than guess it, so results carry page numbers, bounding-box geometry and provenance, tables keep their rows, columns and cells instead of collapsing into flat text, and scanned documents go through an OCR path whose output stays linked to the page evidence. Trust signals for hidden or adversarial text can be requested. Processing is local, so PDFs never require a cloud vision service. The engine itself is a native Rust binary selected per platform through an optional npm package for macOS arm64 and x64, Linux x64 and arm64, and Windows x64; if the native package is missing the server fails closed rather than silently falling back to a JavaScript PDF engine. The maintainers document the resulting install footprint against the earlier TypeScript lineage, reporting a substantially smaller node_modules tree and far fewer installed files. The repository also carries positioning, competitive, evidence contract and tool surface documents plus an agent skill definition, and typical uses named are financial reports, research papers and scanned documents.
https://github.com/SylphxAI/pdf-reader-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.