Red Team

Provides multi‑provider access and multi‑agent coordination via MCP, with local server, dashboard, and client integrations.

python

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "redteammcp-redteam-mcp": {
      "command": "python",
      "args": [
        "main.py",
        "mcp"
      ],
      "env": {
        "GROQ_API_KEY": "YOUR_API_KEY",
        "GOOGLE_API_KEY": "YOUR_API_KEY",
        "OPENAI_API_KEY": "YOUR_API_KEY",
        "DEEPSEEK_API_KEY": "YOUR_API_KEY",
        "ANTHROPIC_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Red Team MCP is a multi-agent collaboration platform that connects to dozens of providers and models, allowing you to assemble specialized agent teams, coordinate complex workflows, and integrate with common development tools through the Model Context Protocol (MCP). It provides a fast API backend, a web dashboard, and production-ready features to manage agents, teams, and usage analytics in one place.

How to use

You run the MCP server locally to expose a Model Context Protocol interface that your AI assistants can connect to. Use the server to coordinate multiple agents across predefined or custom teams, then interact with agents through your preferred MCP client. You can connect from development environments like VS Code and Claude Desktop, or use the built‑in web dashboard to chat with agents, manage teams, and monitor usage.

How to install

Prerequisites: you need Python and optionally Docker if you choose the Docker route. You should also have a modern shell and network access to install dependencies.

# Option A: Docker (Recommended)

git clone https://github.com/yourusername/red-team-mcp.git
cd red-team-mcp
cp .env.example .env
# Edit .env with your API keys

docker compose up -d
# Open http://localhost:8000/ui/

If you prefer a local Python environment without Docker, use a virtual environment and install dependencies, then start the server or use the CLI for interactive chat.

git clone https://github.com/yourusername/red-team-mcp.git
cd red-team-mcp
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt
cp .env.example .env
# Edit .env with your API keys

Configure API keys in your environment or in the .env file, then start the MCP server using the provided entry points.

# Start the web server and dashboard
python main.py serve
# Open http://localhost:8000/ui/

# Or run the MCP server directly
python main.py mcp

# Optional interactive chat via CLI
python main.py chat "What is machine learning?"

Configuration and run-time notes

Environment variables shown in the project cover the core providers. You typically set keys for Anthropic, OpenAI, Google, Groq, and DeepSeek, among others. You can customize providers and models in the configuration files to suit your environment.

# Core providers (examples)
ANTHROPIC_API_KEY=your_key
OPENAI_API_KEY=your_key
GOOGLE_API_KEY=your_key
GROQ_API_KEY=your_key
DEEPSEEK_API_KEY=your_key

# And 60+ more providers supported!

MCP integration and client usage

The platform exposes an MCP server that your AI assistants can connect to. You can interact with agents, run predefined teams, and coordinate multi-agent tasks from MCP-enabled clients. The integration supports VS Code via a configuration file and Claude Desktop with a dedicated MCP server entry, enabling seamless access to agent capabilities from your preferred tools.

Available tools

list_agents

List all available agents within the MCP environment

list_teams

List all predefined and custom agent teams

chat

Chat with a specific agent through the MCP interface

run_team

Execute a predefined or custom team on a given task

coordinate

Run multi-agent coordination across agents and modes

brainstorm

Generate multiple perspectives on a topic

Built by

VeilStrat

AI signals for GTM teams