Best Nat AI Skills & MCP Servers

Agent-native CLI for AI mobile testing and app automation across iOS, Android, tvOS, Android TV, macOS, and Linux.

MCP server for agent-native secrets management — store, rotate, and inject secrets without agents seeing raw values

Planu — MCP Server for Spec Driven Development with native Rust acceleration for hot paths. Cross-platform (Linux/macOS/Windows, x64/arm64, glibc/musl).

Safari browser automation for AI agents — native macOS, zero Chrome overhead. 80 tools via AppleScript + JavaScript.

Planu — MCP Server for Spec Driven Development with native Rust acceleration for hot paths. Cross-platform (Linux/macOS/Windows, x64/arm64, glibc/musl).

Agent Output Guard MCP Server - Validate and verify data from other agents before acting on it. Zero LLM costs, pure computation. Solves coordination failures in multi-agent systems.

Official TypeScript/JavaScript SDK for Licentric — license keys, machine activation, offline validation, AI agent monetization, and Stripe-driven license provisioning. Alternative to Keygen, Cryptlex, LemonSqueezy License Keys.

Planu — MCP Server for Spec Driven Development with native Rust acceleration for hot paths. Cross-platform (Linux/macOS/Windows, x64/arm64, glibc/musl).

Planu — MCP Server for Spec Driven Development with native Rust acceleration for hot paths. Cross-platform (Linux/macOS/Windows, x64/arm64, glibc/musl).

Deploy Claude Code, Codex & Antigravity (agy) CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Per-call model pinning, conversation continuation & intelligent pagination.

Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)

Governance-first recursive cognition infrastructure — LuisCore Chorus Field MCP client + agent CLI (bootstrap, post, feed)

MCP server for runtime quality validation of AI agent outputs — hallucination detection, scope compliance, and output quality scoring

Notion MCP server for Claude, Cursor, ChatGPT, and Claude Desktop — connect AI agents to Notion via the Model Context Protocol. Create pages, query databases, append blocks, upload files, and more in natural language.

Behavioral governance layer for LLMs - monitors for hallucination, inconsistency, tone drift, and unsafe reasoning while managing stateful AI sessions

The Control Plane for AI Agents. 26,701 discoverable APIs, 2,906 callable, 49 fully managed. Agent-native auth: `apiclaw auth login` opens your browser, one-tap sign-in, writes ~/.apiclaw.toml. Four doors: local MCP, CLI, HTTP gateway, Remote MCP. One aut

MCP server for the Agent Passport System — protocol-layer tools only. 150 tools (132 protocol + 10 gateway deprecation stubs). Identity, delegation, reputation, attestation, coordination, commerce, attribution primitive, attribution settlement. Tracks SDK

Deploy any web project with one command. AI-native deployment platform.

Agent-native MCP server for TokRepo - discover, verify, plan, safely install, hand off, and push AI assets from MCP clients.

Enterprise-grade MCP server for live docs, best practices, code audit. Context7 alternative — 445+ libraries, smart dispatch (use gt mcp), plain-text intent routing, telemetry, SSRF-hardened multi-source fetcher, atomic disk cache, IPv6 + Unicode-homoglyp

Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a built-in verification loop. Works on every Figma plan including Free. Drop-in alternative to Figma's Dev Mode MCP and Framelink for Claude Code, Cursor, Windsurf, and any

Model Context Protocol (MCP) server for the A2A (Agent2Agent) protocol compliance test kit. Lets Claude Desktop, Cursor, Codex, and other MCP clients invoke run_compliance / validate_agent_card / list_checks / explain_check / ssrf_check_url as native tool

MCP server for macOS Mail.app — gives Claude native email access via AppleScript

AINative ZeroDB MCP Server - 77 operations for vector search, quantum compression, NoSQL, dedicated PostgreSQL management, files, events, RLHF, and persistent memory for AI agents with enterprise security. All tools annotated with readOnly/destructive/ide