home / mcp / onsched consumer mcp server
MCP Server generated by mcp.ag2.ai
Configuration
View docs{
"mcpServers": {
"ag2-mcp-servers-onsched-consumer-api": {
"command": "python",
"args": [
"mcp_server/main.py",
"stdio"
],
"env": {
"CONFIG": "{...}",
"SECURITY": "YOUR_API_KEYS",
"CONFIG_PATH": "mcp_server/mcp_config.json"
}
}
}
}This MCP Server provides a standardized way to serve your Model Context Protocol endpoints from a predefined OpenAPI source. It lets you connect with MCP clients to access context-aware APIs in a consistent, scalable manner, enabling streamlined integration and testing across services.
Start the server in stdio mode to enable a local IPC-based MCP connection that your client can interact with directly. You will run a single command to launch the server, and then your MCP client can exchange requests and responses through the established channel. Use this mode when you want fast, local development feedback and straightforward debugging.
Prerequisites include Python 3.9+ and the uvicorn utility (uv) for development workflows.
# 1) Clone the repository
git clone <repository-url>
cd mcp-server
# 2) Install dependencies (dev environment)
pip install -e ".[dev]"
# Alternatively, using uv for editable installs
uv pip install --editable ".[dev]"Running the server supports multiple transport modes; stdio is the recommended local development mode, while other modes may be available for remote or streaming usage. The server accepts configuration through environment variables to customize its behavior.
Environment variables you can use include: - CONFIG_PATH: Path to a JSON configuration file (for example, mcp_server/mcp_config.json) - CONFIG: A JSON string containing the configuration - SECURITY: Environment variables for security parameters (e.g., API keys)
To run the server in stdio mode (the most common local development pattern), use the following command.
python mcp_server/main.py stdio