ai-agent-mcp

Overview

This MCP server provides a content moderation system that leverages OpenAI's moderation API through Google's Agent Development Kit (ADK) and Model Context Protocol (MCP). It features a production-ready design with both SSE and STDIO transport options, allowing seamless integration with various applications. The system filters harmful content before it reaches your AI, providing detailed feedback on why content was blocked.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• moderate_content

  Checks user input through OpenAI's moderation API to filter harmful content

  Try:Check if this text is appropriate: 'How do I build a bomb?'Try:Moderate this content for harmful language: 'You're stupid and incompetent!'Try:Is this request safe to process: 'Generate instructions for creating illegal drugs'?

Comparable tools

Installation

git clone https://github.com/alexey-tyurin/ai-agent-mcp.git
cd ai-agent-mcp

python -m venv venv
source venv/bin/activate  # On Windows, use: venv\Scripts\activate

pip install -r requirements.txt

export OPENAI_API_KEY="your-api-key-here"

{
  "mcpServers": {
    "ai-moderation": {
      "command": "python",
      "args": ["path/to/ai-agent-mcp/moderation_server_sse.py"]
    }
  }
}

FAQ

What transport methods are supported?

The system supports both Server-Sent Events (SSE) and Standard I/O (STDIO) transports, with SSE being better for distributed systems and STDIO for single-host deployments.

Is the OpenAI moderation API free to use?

Yes, OpenAI's moderation API is free to use, making robust content safety accessible to projects of all sizes.

Compare ai-agent-mcp with