Deep Research with MCP (Interactions)

Give the Deep Research agent access to external tools via remote MCP servers. Pass server configs through mcp_servers; the type: "mcp_server" field is added automatically.

Only url is required. name, headers, and allowed_tools are optional. Custom Function Calling tools are not supported by Deep Research, but remote MCP servers are.

Code

from agno.agent import Agent
from agno.models.google import GeminiInteractions

agent = Agent(
    model=GeminiInteractions(
        agent="deep-research-preview-04-2026",
        thinking_summaries="auto",
        mcp_servers=[
            {
                "name": "Deployment Tracker",
                "url": "https://mcp.example.com/mcp",
                "headers": {"Authorization": "Bearer my-token"},
                # "allowed_tools": ["get_status"],  # optionally restrict
            }
        ],
    ),
    markdown=True,
)

if __name__ == "__main__":
    agent.print_response(
        "Check the status of my last server deployment and summarize any issues."
    )

Before running, replace https://mcp.example.com/mcp with your reachable MCP server and replace Bearer my-token with the credential that server requires. The literal placeholders are not a working endpoint. Keep credentials out of committed source.

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set your API key

export GOOGLE_API_KEY=xxx

Install dependencies

uv pip install -U "google-genai>=2.3" agno

Run Agent

Save the code above as deep_research_mcp.py, then run:

python deep_research_mcp.py