Skip to main content
Glama
power-mcp

power-mcp

by viperrxd

⚑ Power-MCP

Secure Cloud Model Context Protocol (MCP) Server for Antigravity AI

power-mcp is a custom Model Context Protocol server built for Google's Antigravity ecosystem. It equips your autonomous AI agents with elite-level Full-Stack Developer and Cyber Security Expert capabilities. By utilizing Server-Sent Events (SSE) over HTTP, this toolset is decoupled from localhost, allowing your Antigravity agents to securely access these capabilities from any device.

πŸ›‘οΈ Core Features

  • Universal Device Access: Cloud-deployed SSE transport allows you to use your custom tools anywhere.

  • Ironclad Security Layer: Unbypassable API key authorization prevents unauthorized tool execution.

  • Automated CI/CD: Docker images are automatically built and published to the GitHub Container Registry (GHCR) via GitHub Actions.


Related MCP server: mcp-remote-ssh

πŸ› οΈ Available AI Tools

1. audit_security_headers

Analyzes a given URL/endpoint for required OWASP security headers. Ensures the agent strictly enforces Content-Security-Policy (CSP) and HTTP Strict Transport Security (HSTS).

2. validate_gsap_timeline

Analyzes GSAP timeline and WebGL code snippets for layout shift risks and memory leaks. Forces the agent to maintain a locked 60+ FPS by validating that only composited properties are animated.


πŸš€ Getting Started

The fastest and most secure way to run power-mcp is by using our pre-built Docker image hosted on the GitHub Container Registry. You must provide a secure API key to start the server.

You do not need to clone the repository or build the code. Just pull the latest image directly from GHCR:

docker run -p 3000:3000 -e MCP_API_KEY="your_secure_secret_key" ghcr.io/viperrxd/power-mcp:latest

Method 2: Manual Repository Build (Node.js)

If you want to modify the source code locally without Docker:

git clone [https://github.com/viperrxd/power-mcp.git](https://github.com/viperrxd/power-mcp.git)
cd power-mcp
npm install
npm run build
export MCP_API_KEY="your_secure_secret_key"
npm start

☁️ Cloud Deployment

This server is packaged as a standard Node.js application and includes a Dockerfile, making it fully optimized for deployment on any modern Cloud Provider or Platform-as-a-Service (PaaS).

To deploy your own private instance:

  1. Connect your repository or deploy the provided Docker container to your preferred hosting platform.

  2. Environment Variables: You must configure an MCP_API_KEY environment variable. Set this to a highly secure, randomized cryptographic string.

  3. Port Binding: Ensure your platform routes web traffic to port 3000 (or dynamically injects the PORT environment variable).


πŸ”Œ Antigravity Ecosystem Integration

Once your server is running (locally or in the cloud), connect it to your Antigravity IDE or Antigravity 2.0 app. Add this block to your mcp_config.json:

{
  "mcpServers": {
    "power-mcp": {
      "type": "sse",
      "url": "https://YOUR_DEPLOYED_URL/sse?key=YOUR_SECURE_API_KEY"
    }
  }
}

Note: If running locally via Docker, replace the URL with http://localhost:3000/sse?key=YOUR_SECURE_API_KEY.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      MCP server for secure, just-in-time secret retrieval from 1claw vault and malicious content inspection, enabling AI agents to access secrets and security analysis.
      1
      560 npm
      4
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      MCP server giving AI agents full SSH access with persistent sessions, structured command output, SFTP file transfer, and port forwarding.
      18
      12
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An AI Security Guardian MCP server that provides real-time vulnerability scanning, secrets detection, and secure coding enforcement for AI-generated code in modern web frameworks.
      MIT