AI Content Moderation System with Google AI agent and Model Context Protocol (MCP)
A content moderation system that leverages OpenAI's moderation API through Google's Agent Development Kit (ADK) and Model Context Protocol (MCP).
Power your agent
Install from the publisher. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
No packaged release in the registry yet. Follow the repository README.
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchFrom the publisher
A content moderation system that leverages OpenAI's moderation API through Google's Agent Development Kit (ADK) and Model Context Protocol (MCP).
A content moderation system that leverages OpenAI's moderation API through Google's Agent Development Kit (ADK) and Model Context Protocol (MCP).
Imagine this: You've just launched your exciting new AI chatbot. Users are flooding in, conversations are happening, and everything seems perfect—until it's not.
A user asks your AI how to build an explosive device. Another probes for inappropriate content. Someone else tests the boundaries with harmful language. Suddenly, your innovative AI tool has become a potential liability.
This is the reality many AI developers face today.
Without proper content moderation, AI systems can:
This is where our AI Content Moderation System comes in. We've built a production-ready solution that:
The best part? OpenAI's moderation API is free to use, making robust content safety accessible to projects of all sizes.
This system isn't just a technical demo—it's designed for real production use cases:
This project implements two variants of a content moderation flow:
┌────────────┐ ┌──────────────┐ ┌──────────────┐ ┌─────────────┐
│ User Query │───→│ ADK Agent │───→│ MCP Client │───→│ MCP Server │
│ │←───│ (SSE Client) │←───│ (Moderation) │←───│ (SSE) │
└────────────┘ └──────────────┘ └──────────────┘ └────────┬────┘
↑ ↑ │
│ Moderation Response │ ↓
│ ┌─────────────┐
│ │ OpenAI │
│ │ │
│ │ API │
│ └─────────────┘
│
↓
┌────────────────────┐
│ Llama LLM │
│ (Content Response) │
└────────────────────┘
┌────────────┐ ┌──────────────┐ ┌──────────────┐ ┌─────────────┐
│ User Query │───→│ ADK Agent │───→│ MCP Client │───→│ MCP Server │
│ │←───│ (STDIO) │←───│ (Moderation) │←───│ (STDIO) │
└────────────┘ └──────────────┘ └──────────────┘ └────────┬────┘
↑ ↑ │
│ Moderation Response │ ↓
│ ┌─────────────┐
│ │ OpenAI │
│ │ │
│ │ API │
│ └─────────────┘
│
↓
┌────────────────────┐
│ Llama LLM │
│ (Content Response) │
└────────────────────┘
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" # On Windows, use: set OPENAI_API_KEY=your-api-key-here
python moderation_server_sse.py
python moderation_agent_sse.py
python moderation_agent_stdio.py
Run the comprehensive test script to check all components:
python test_moderation_system.py
Or test individual components:
# Test server in standalone mode
python moderation_server_sse.py --test
# Test agent with simulated moderation (no server needed)
python moderation_agent_sse.py --test
# Test the moderation tool directly
python moderation_agent_sse.py --test-tool "Test content to moderate"
Containerization using Docker and Kubernetes is a popular approach for deploying MCP servers in cloud environments. This provides:
Serverless options like AWS Lambda, Google Cloud Functions, or Azure Functions can be used for MCP servers that don't require persistent connections. Benefits include:
Major cloud providers offer managed services that can host MCP servers:
These services handle infrastructure scaling while you focus on the application logic.
Traditional on-premises deployment involves installing the MCP server directly on physical servers in your data center. This offers:
Deploy MCP servers on private cloud infrastructure using technologies like OpenStack or VMware vSphere. This provides:
For latency-sensitive applications, MCP servers can be deployed at the edge, closer to where data is generated and consumed. Benefits include:
Many organizations opt for hybrid deployment strategies:
When choosing a deployment option, consider these factors:
For any questions or feedback, please contact Alexey Tyurin at [email protected].
This project is licensed under the MIT License - see the LICENSE file for details.
A content moderation system that leverages OpenAI's moderation API through Google's Agent Development Kit (ADK) and Model Context Protocol (MCP).
Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
No required environment variable is listed on this record.
Ai Agent runs locally over stdio.
Last checked 2026-10-28. A content moderation system that leverages OpenAI's moderation API through Google's Agent Development Kit (ADK) and Model Context Protocol (MCP).