Best LLM AI Skills & MCP Servers
472 curated LLM skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Gmail
Gmail MCP server — scope-gated tools + attachment/download path jails + supply-chain hardening. Fork of GongRzhe/Gmail-MCP-Server via ArtyMcLabin's intermediate fork.
Server
NestJS MCP Server - Build Model Context Protocol servers with NestJS
Ollama Intern
MCP control plane for local cognitive labor — job-shaped tools with tiered Ollama models (instant/workhorse/deep/embed), server-enforced guardrails, and measured economics so Claude can delegate bulk work without losing control.
Lazy
A proxy tool that converts normal MCP servers to use lazy-loading pattern with three/four meta-tools
Agent Security Scanner
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1700+ vulnerability rules with AST & taint analysis, LLM-powered semantic code review, auto-fix. For Claude Code, Cursor, Windsu
Code Graph Context
MCP server that builds code graphs to provide rich context to LLMs
Git
An MCP (Model Context Protocol) server enabling LLMs and AI agents to interact with Git repositories. Provides tools for comprehensive Git operations including clone, commit, branch, diff, log, status, push, pull, merge, rebase, worktree, tag management,
Antigravity Plugin Manager
Antigravity-CLI Plugin. 309 community agent skills aggregated from 13 popular open-source repositories, one-command install.
Server
RushDB MCP Server - Model Context Protocol server for RushDB
Tuningengines Cli
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p
Code Council
Multi-model AI code review server using OpenRouter - get diverse perspectives from multiple LLMs in parallel
Yaml
Declarative MCP Server Engine — define tools, resources, and prompts in vurb.yaml. The docker-compose for MCP servers.
Bullmq
Model Context Protocol server for BullMQ job queue management
Finmap
MCP server providing financial market data from finmap.org
Server
MCP server for Decantr — exposes Contract context, typed graph artifacts, and verification evidence to AI coding assistants
Core
Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)
Mcp
MCP server + live dashboard for AI code governance — OWASP LLM Top 10 (10/10), real-time MCP App UI, 25+ security patterns, Bayesian learning Brain, hallucinated import detection, multi-agent governance. Works with Claude, Cursor, VS Code, ChatGPT, Goose,
Mongo Server
A Model Context Protocol server for MongoDB connections
Ask Llm
Unified MCP server for multi-LLM consultation — registers tools from all available providers (Gemini, Codex, Ollama) behind runtime availability checks
Cctx Optimizer
Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en
Freshcontext
Real-time web intelligence for AI agents. 21 tools, no required API keys. Every result timestamped with a freshness score.
Mcpollinations
Model Context Protocol (MCP) server for the Pollinations APIs with image saving functionality.
Ask Ollama
MCP server for local Ollama LLM integration - for Claude IDE and other IDEs
Server Atlassian Bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MC
About LLM skills on iClaude
iClaude is the universal install layer for AI skills. Every LLM skill on this page can be installed into Claude Code, Claude Desktop, Cursor, ChatGPT, n8n, Codex, and more — using a single copy-paste command. No config drift, no per-stack adapters, no manual MCP wiring.