pip install -e .

# Using stdio transport (default) mcp-server-lls # Using SSE transport on custom port mcp-server-lls --transport sse --port 8000

# Using stdio transport (default) uv run mcp-server-lls # Using SSE transport on custom port uv run mcp-server-lls --transport sse --port 8000

from llama_stack_client.lib.agents.agent import Agent from llama_stack_client.lib.agents.event_logger import EventLogger from llama_stack_client.types.agent_create_params import AgentConfig from llama_stack_client.types.shared_params.url import URL from llama_stack_client import LlamaStackClient import os # Set your model ID model_id = os.environ["INFERENCE_MODEL"] client = LlamaStackClient( base_url=f"http://localhost:{os.environ.get('LLAMA_STACK_PORT', '8080')}" ) # Register MCP tools client.toolgroups.register( toolgroup_id="mcp::docling", provider_id="model-context-protocol", mcp_endpoint=URL(uri="http://0.0.0.0:8000/sse")) # Define an agent with MCP toolgroup agent_config = AgentConfig( model=model_id, instructions="""You are a helpful assistant with access to tools to manipulate documents. Always use the appropriate tool when asked to process documents.""", toolgroups=["mcp::docling"], tool_choice="auto", max_tool_calls=3, ) # Create the agent agent = Agent(client, agent_config) # Create a session session_id = agent.create_session("test-session") def _summary_and_qna(source: str): # Define the prompt run_turn(f"Please convert the document at {source} to markdown and summarize its content.") run_turn(f"Please generate a Q&A document with 3 items for source at {source} and display it in YAML format.") def _run_turn(prompt): # Create a turn response = agent.create_turn( messages=[ { "role": "user", "content": prompt, } ], session_id=session_id, ) # Log the response for log in EventLogger().log(response): log.print() _summary_and_qna('https://arxiv.org/pdf/2004.07606')