Skip to content

Bringing Human Capabilities
to AI Agents

29 MCP tools that give your AI agents eyes to see, hands to create, a mouth to speak, and a brain to reason.

$ npx @goonnguyen/human-mcp
29
MCP Tools
6+
AI Providers
24
Languages

Human-Like Capabilities

Everything your AI agent needs to interact with the world like a human.

👁️
4 tools

Eyes - Visual Analysis

Analyze images, videos, GIFs for UI bugs & accessibility. Compare visuals, extract text from PDFs, DOCX, XLSX, and more.

18 tools

Hands - Content Creation

Generate images, videos, music, sound effects. AI-powered editing with inpainting, style transfer, background removal.

🗣️
4 tools

Mouth - Speech Generation

Text-to-speech with 30+ voices across 24 languages. Long-form narration, code explanation, and voice customization.

🧠
3 tools

Brain - Advanced Reasoning

Sequential thinking with revision, fast pattern analysis (SWOT, root cause), and meta-cognitive reflection.

Powered by Leading AI

Leverage the best AI models from multiple providers for each capability.

Google Gemini
Vision, Images, Video, Speech
ElevenLabs
Speech, Music, Sound Effects
Minimax
Video, Music Generation
ZhipuAI
Vision, Image, Video
Playwright
Browser Automation
Sharp / Jimp
Local Image Processing

Up & Running in 60 Seconds

One command to install, one config to connect. That's it.

1

Get API Key

Create a free key at Google AI Studio — aistudio.google.com

2

Set Environment

Export your API key

export GOOGLE_GEMINI_API_KEY="your_key"
3

Add to Config

Add to your MCP client configuration

{
  "mcpServers": {
    "human-mcp": {
      "command": "npx",
      "args": ["@goonnguyen/human-mcp"],
      "env": {
        "GOOGLE_GEMINI_API_KEY": "your_key"
      }
    }
  }
}

Part of the Ecosystem

Human MCP is built and maintained by the teams behind ClaudeKit and GoClaw.

Give Your AI Agent Human Superpowers

Join developers who are building smarter AI agents with Human MCP.