AgenticMaid Project

Multi-Server MCP Interaction: Connects to and utilizes tools from multiple MCP servers.
Dynamic Tool Fetching: Retrieves available tools from MCP servers at runtime.
Flexible Configuration: Supports configuration via Python dictionaries, JSON files, and .env files for sensitive data.
AI Service Management: Configures and utilizes various AI/LLM services (e.g., OpenAI, Anthropic, Azure OpenAI, local models).
Scheduled Tasks: Allows defining and running tasks based on cron-like schedules.
Chat Service Integration: Provides a framework for handling interactions with defined chat services.
Agent Creation: Uses langgraph to create ReAct agents that can leverage MCP tools and configured LLMs.
Environment Variable Support: Loads default configurations and sensitive keys (like API keys) from an .env file.

AgenticMaid also provides a command-line interface (CLI) tool to execute all enabled scheduled tasks based on a provided configuration file. This is useful for batch processing or running tasks from a terminal or script.

To use the CLI tool:

Ensure the AgenticMaid package and its dependencies are accessible in your PYTHONPATH.

From the root directory of the Agent project, you can run the CLI module as follows:

python -m AgenticMaid.cli --config-file path/to/your/config.json

Arguments:

• --config-file (required): Path to the JSON configuration file for AgenticMaid. This file should define ai_services, mcp_servers, and scheduled_tasks as needed. Refer to AgenticMaid/config.example.json for the structure.

1. The CLI tool will load the specified configuration file.
2. It will initialize an ClientAgenticMaid instance with this configuration.
3. It will then attempt to execute all tasks listed in the scheduled_tasks section of the configuration that have "enabled": true.
4. Output, including task execution status and any results or errors, will be logged to the console.

Example Command:

python -m AgenticMaid.cli --config-file ./AgenticMaid/config.example.json

This command will run all enabled scheduled tasks defined in AgenticMaid/config.example.json. Check the console output for details on each task's execution.

The original "Examples" section is now renumbered.

]]>

"my_mcp_server": {
"adapter_type": "fastapi",
"base_url": "http://localhost:8001/mcp/v1", # Replace with your actual MCP server URL
"name": "Example MCP Server"
}
},
"scheduled_tasks": [
{
"name": "Test Scheduled Task",
"cron_expression": "daily at 00:00", # Will run once if current time is past 00:00 and scheduler is kept running
"prompt": "This is a test scheduled prompt. What time is it using Gemini?",
"model_config_name": "default_llm",
"enabled": True # Set to False if you don't want it to run
}
],
"chat_services": [
{
"service_id": "test_chat_gemini",
"llm_service_name": "default_llm"
},
{
"service_id": "test_chat_claude",
"llm_service_name": "claude_opus_llm"
}
],
"default_llm_service_name": "default_llm"
}

client = ClientAgenticMaid(config_path_or_dict=config)
await client.async_initialize()

if not client.config:
print("Client configuration failed. Exiting.")
return

print(f"ClientAgenticMaid Initialized. Config Source: {client.config_source}")
print(f"Available MCP Tools: {[tool.name for tool in client.mcp_tools] if client.mcp_tools else 'No tools fetched (check MCP server config and availability)'}")

print("Make sure your .env file (in AgenticMaid directory) has GOOGLE_API_KEY and ANTHROPIC_API_KEY set for this example to fully work.")
print("Also, ensure an MCP server is running at the configured URL if you expect MCP tools.")
asyncio.run(run_client_operations())

``

This README provides a comprehensive guide to installing, configuring, and using the ClientAgenticMaid`. Remember to adapt paths and configurations to your specific project setup.