Skip to main content

Agent Registry — Agno

Wire a LumoAuth-registered agent into Agno. The agent's identity is its registered AGENT_CLIENT_ID in LumoAuth; it authenticates via OAuth 2.0 client credentials (the LumoAuthAgent class handles this); tools call has_capability(...) before executing; for an MCP tool call, the code exchanges the base access token for an MCP-bound token via RFC 8693 — OAuth 2.0 Token Exchange (swap one token for another, audience-bound to the target MCP server).

Prerequisites

Install the lumoauth package and set the environment variables LUMOAUTH_URL, LUMOAUTH_ORG_ID, AGENT_CLIENT_ID, and AGENT_CLIENT_SECRET. See Install the SDK.

Install​

pip install lumoauth agno openai

Example​

from agno.agent import Agent
from agno.tools import tool
from agno.models.openai import OpenAIChat
from lumoauth import LumoAuthAgent

# 1. Initialize and authenticate the LumoAuth Agent
lumo_agent = LumoAuthAgent()
lumo_agent.authenticate()

# 2. Define tools that check LumoAuth capabilities
@tool
def search_company_documents(query: str) -> str:
    """Search internal company documents for the given query."""
    if not lumo_agent.has_capability('read:documents'):
        return "Error: Agent lacks 'read:documents' capability."
    return f"Found 3 documents matching '{query}'"

@tool
def query_financial_mcp(metric: str) -> str:
    """Query the secured financial metrics MCP server for a given metric."""
    if not lumo_agent.has_capability('mcp:financial'):
        return "Error: Agent lacks 'mcp:financial' capability."
    mcp_token = lumo_agent.get_mcp_token("urn:mcp:financial-data")
    if not mcp_token:
        return "Error: Failed to obtain token for Financial MCP server."
    return f"Retrieved {metric}: $1.2M (Authenticated via MCP Token Exchange)"

# 3. Check budget before running
if lumo_agent.is_budget_exhausted():
    raise RuntimeError("Agent budget exhausted for today.")

# 4. Create and run the Agno Agent
agent = Agent(
    name="Research Analyst",
    model=OpenAIChat(id="gpt-4"),
    tools=[search_company_documents, query_financial_mcp],
    instructions=[
        "You are a senior analyst at a financial firm.",
        "Use tools to search documents and query financial metrics.",
    ],
    markdown=True,
)

agent.print_response(
    "Search documents for Q3 performance, then query the financial MCP for EBITDA."
)

How it works​

StepWhat happens
LumoAuthAgent()Reads credentials from env vars and initializes the client
lumo_agent.authenticate()Runs the OAuth 2.0 client-credentials flow
has_capability(...)Guards tool execution with LumoAuth capability checks
get_mcp_token(...)Swaps the agent token for an MCP-specific token (RFC 8693)
is_budget_exhausted()Prevents the Agno run if the agent's daily budget is spent

Next steps​