A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
180 packages found
An open framework for scoring how well an MCP tool definition communicates to an AI agent – the Tool Definition Quality
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex,
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, pages, and more from any AI agent
Roslyn-powered MCP server for AI-driven C# semantic analysis, refactoring, and code generation
MCP server providing semantic Java code analysis for AI agents. Built on Eclipse JDT with tools for navigation, refactor
Your coding agent is editing blind. agent-lsp gives it type-aware navigation, blast-radius analysis, and pre-verified ed
✈️ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search
AI coding rules that actually work. Enforce instruction files via hooks — CLAUDE.md, .cursorrules, copilot-instructions,
Code intelligence for AI assistants - MCP server, CLI, and HTTP API with symbol navigation, impact analysis, and archite
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops
Design intelligence engine for AI coding tools (Claude Code, Cursor, Windsurf). Deterministic anti-AI-slop linter with 1
Agents, commands, skills, and scripts for scaffolding, reviewing, aligning, and deploying Claude Code, Codex & Gemini pl
Agent Skill: TYPO3 extension conformance checker - validates against official standards | Claude Code compatible
Debugging-first MCP server for n8n. Tools for workflow generation, linting, per-node execution diagnosis, and driving li
A Research Cortex. A research companion for Claude. Your library, notes & memory stay on your machine; answers cited fro
The first MCP server for Guesty property management. 38 tools for reservations, guests, messaging, pricing, financials,
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review e
The ultimate Web3 Growth & Research MCP Server. Equip your AI agent with data to run wallet forensics for traders and DA
Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool
A tool-agnostic AI-assisted development framework template. Structured workflow (Spec → Plan → Implement → Review) with
Metacog isn't memory for LLMs, it gives them a nervous system. Metacognition developed on your unique user experiences.
The missing context layer for AI-assisted refactoring
Hooks that force Claude Code to use LSP instead of Grep for code navigation. Saves ~80% tokens
Local multi-agent coding orchestrator with 22 pipeline roles, TDD enforcement, SonarQube integration, and automated code
Extended GitHub MCP Server with additional tools for pull request review comment functionality
PHP static analysis for architecture & maintainability — 60+ metrics, complexity analysis, dependency graphs, git churn
A Model Context Protocol (MCP) tool that automates code review and leaves comments directly on GitHub PRs, with support
An engineering team in a box for Claude Code — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology
SPEC-First Agentic Development Kit for Claude Code — 24 AI agents + 52 skills with TDD/DDD quality gates, 16-language pr
Make any repo AI-first - write sustainable code from the start, or refactor a legacy codebase to prepare it for agent-dr
It's a plugin extension in Zotero. Zotero MCP Plugin enables integration between AI assistants and Zotero through MCP.
MCP prompt template server: hot-reload, thinking frameworks, quality gates
Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to i
An MCP server for code reviews using OpenAI and Google models for Claude-code
Lightning-native AI agent platform — pre-trade /review, pay-per-use reasoning, sandboxed execution, persistent memory, a
Session-Driven Development - Maintain perfect context across AI coding sessions with Claude Code
Skills and tools for scientific research with LLM agents. 给 Agent（如 Claude Code、Openclaw）提供的科研 skills
MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in d
Self-hosted AI technical workbench. Visual, persistent, multi-stream. Development, architecture, and operational analyti
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — sel
High-performance MCP server, code graph engine & evolutionary algorithm platform in Zig. 33 tools: GitHub project manage
The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, st
Academic Research Skills for Claude Code: research → write → review → revise → finalize
A framework for designing App Store-compliant subscription paywalls. 4 layers: AI skill (Claude/GPT/Cursor) + knowledge
AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST,
Local-first AI app-builder brain for Claude Code, Codex, and Cursor: archetypes, golden templates, UI/UX playbooks, and
Portable skills, agents, and templates that add Spec-Driven Development and TDD workflows to any Claude Code project. De
Code Guardian Studio – AI-powered code refactor engine for large repositories, built on Claude Code + MCP.
@x51xxx