home / mcp / rtb mcp server

RTB MCP Server

MCP Server generated by mcp.ag2.ai

Installation
Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "ag2-mcp-servers-real-time-bidding-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "JSON string containing the configuration",
        "SECURITY": "Environment variables for security parameters such as API keys",
        "CONFIG_PATH": "Path to a JSON config like mcp_server/mcp_config.json"
      }
    }
  }
}

You run an MCP Server that exposes a machine-readable interface for a specific API via a standardized transport. This lets clients query, fetch, and interact with the Real-Time Bidding API in a consistent, protocol-agnostic way, enabling efficient integration and testing across services and applications.

How to use

Start the MCP server locally in stdio mode so you can interact with it from other processes. The server is invoked through Python and runs a single entry script that handles the MCP protocol over standard input and output channels. Once running, you can point an MCP client at it and perform supported operations such as querying data sources and triggering actions defined by the MCP interface.

How to install

# Prerequisites
# Ensure you have Python 3.9+ and a functioning Python environment

# Install runtime dependencies (development helpers)
# Option A: install via pip in editable mode (preferred for quick local development)
pip install -e ".[dev]"

# Option B: use uv to manage installation and execution
uv pip install --editable ".[dev]"

# Run the server in stdio mode
python mcp_server/main.py stdio

Configuration and security notes

Configure how the MCP server loads its settings using environment variables. The following variables are recognized:"CONFIG_PATH" points to a JSON configuration file (for example, mcp_server/mcp_config.json). If you prefer to pass configuration directly, use the JSON string in the "CONFIG" variable. You can also set security-related parameters via "SECURITY" for API keys or other access controls.

Environment variable usage at runtime:

Troubleshooting and notes

If the server does not start as expected, check that Python 3.9+ is installed and that the entry script path (mcp_server/main.py) exists in your working directory. Ensure any required configuration values are provided through CONFIG_PATH or CONFIG, and confirm you are starting the server in stdio mode as shown in the start command.

Tools and development helpers

The project uses several tooling helpers to maintain code quality and reliability. You can run them locally to validate your setup and catch issues early.

Available tools

ruff

Lints and formats the codebase to maintain style and detect issues early.

mypy

Performs static type checking to ensure type correctness across the project.

pytest

Runs the test suite to verify functionality and catch regressions.

pre-commit

Runs a set of hooks before each commit to enforce quality checks.