Claude Code MCP Servers plugins and skills

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Generative UI SDK for React

Hugging Face Skills are definitions for AI/ML tasks like dataset creation, model training, and evaluation.

Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company

Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.

The complete guide to maximizing Claude Code: Global CLAUDE.md, MCP Servers, Commands, Hooks, Skills, and Why Single-Purpose Chats Matter. This version is obsolete by now.

The local-first, agent-native control plane for ComfyUI — an MCP server + live sidebar agent that generates images, video and audio, authors and runs workflows, manages models and custom nodes, and edits your live ComfyUI graph in natural language.

Zapier MCP gives any MCP-compatible AI client governed access to 9,000+ apps — send messages, pull data, trigger workflows, all in plain English. No code, no infrastructure, SOC 2 Type II certified.

Make AI actually work for you — a personal AI harness that writes and repairs its own tools, and lets Claude Code and Codex build and share them via MCP.

Open-source, desktop client/UI build to harness Claude Code, Codex and any other Agent accepting Agent Client Protocol. Run multiple AI coding agents side by side with rich tool visualization, MCP integrations, built-in terminal, git, browser and just about anything else you may need.

Smarter tools for Claude Code that reduce token usage and cost. Replaces built-in file tools with optimized alternatives — fewer tokens per tool call means cheaper sessions that compound over time.

🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.

Modular iOS development automation for Claude Code Build, test, and automate iOS apps through natural conversation with Claude. 8 workflow-specific MCP servers with 24 tools across Xcode, Simulator, and IDB. Enable only what you need.

A collection of skills for AI coding agents working with Apollo GraphQL tools and technologies. Apollo Skills follow the Agent Skills format and are available on skills.sh.

🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

94 Specialized Skills for Blender Artists. Transform Cursor, Claude Code, Kiro, and Codex into your Senior Technical Art team — not a tutorial bot.

Write a skill once, use it everywhere. Skrills validates and syncs skills, commands, agents, MCP servers, and hooks across **Claude Code, Codex CLI, GitHub Copilot CLI, and Cursor**, all from a single Rust binary. Install · User Guide · CLI Reference · FAQ ·

Drive your Claude Code session from WhatsApp — your personal number, no bots, no API keys. The plugin connects to WhatsApp as a linked device (the same protocol as WhatsApp Web, via Baileys) and exposes it to Claude Code as an MCP channel.

Vaaya is the agent payment system: one MCP server that lets any agent call paid APIs pay-per-call, with no API keys.

Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.

Build beautiful games with high-quality 3D assets using Thrixel and Claude Code. Claude Code handles the game logic and scene setup. Thrixel generates, organizes, and manages the 3D assets.

Tandem is an MCP bridge that lets a chatbot (Claude.ai or ChatGPT) spin up and drive, interactive Claude Code sessions on your own machine. Runs 2 sessions in a lead/worker loop that works autonomously. Also makes claude code respond to the initial Chatbot through the browser so it can respond back.

A Claude Code plugin marketplace and Agent Skills collection that teaches your AI coding agent how to drive every programmatic RudderStack surface — CLI, MCP server, Terraform, and Profiles — with the right preflight checks, commands, and recovery paths.

mcpx is a command line tool that turns registered MCP servers into an agent-friendly command surface.

Trust metadata for AI agents — a stamp costs ~15 tokens, re-verifying costs 15,000. Agents stamp what they verify; the next agent runs 'akf check' and builds on it. pip install akf

Live AI coding monitor — real-time trace, quota guard, and MCP server Most tools read your logs after a session ends. claudestat hooks into every event as it fires.

Opinionated, first-party agent skills, plugins, subagents, slash commands, and MCP servers for the Litestar framework and its ecosystem — publishable to every major AI agent and IDE from a single repo.

Clearfront OSINT: free, open-source AI OSINT agent that maps your digital footprint across 3,400+ public data sources. REPL, CLI, web console, MCP server.

Interacts with WinForms UI elements and captures screenshots of headlessly rendered forms through an MCP server. Fires when automating or testing C# desktop UI without a visible display.

Local stdout/stderr capture for AI coding agents. Run any process under trail, then ask Codex, Claude Code, Cursor, Windsurf, or another MCP-capable agent to query the captured logs without pasting terminal output into chat. Single static binary.

A free, self-hosted MCP server that tells your agent what LLMs cite - across Perplexity, Google AI Overviews, ChatGPT, Claude, Gemini, and Bing.

Vizier - the decision-making brain of an agentic-trading stack. A Claude Code skill that researches, decides, remembers and orchestrates trades across US stocks/ETFs (IBKR) and crypto spot (CCXT), driving the Scout and Valet MCP servers it never modifies. Hybrid skill + deterministic safety core; paper-first.

Hypothesis-driven problem solving for AI agents Probe · Falsify · Escalate — never overcomplicate, never blind-retry