Agent Registry — CrewAI

Connect a LumoAuth-registered agent to CrewAI. The agent's identity is its registered AGENT_CLIENT_ID. It authenticates via OAuth 2.0 client credentials (via LumoAuthAgent). Tools check has_capability(...) before running. MCP tools swap the base access token for one bound to the MCP server using token exchange. (MCP is the Model Context Protocol, the standard way for agents to call tool servers.)

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 crewai crewai-tools

Example

from crewai import Agent, Task, Crew
from crewai.tools import tool
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("https://mcp.example.com/finance")
    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 CrewAI agents and tasks
researcher = Agent(
    role="Research Analyst",
    goal="Find relevant company documents and financial metrics",
    backstory="You are a senior analyst at a financial firm.",
    tools=[search_company_documents, query_financial_mcp],
    verbose=True,
)

research_task = Task(
    description="Search documents for Q3 performance, then query the financial MCP for EBITDA.",
    expected_output="A summary of Q3 performance with EBITDA figures.",
    agent=researcher,
)

# 5. Assemble and run the Crew
crew = Crew(agents=[researcher], tasks=[research_task], verbose=True)
result = crew.kickoff()
print(result)

How it works

Step	What happens
`LumoAuthAgent()`	Reads credentials from environment variables and initializes the client
`lumo_agent.authenticate()`	Runs the OAuth 2.0 client-credentials flow
`has_capability(...)`	Checks the agent's LumoAuth capabilities before a tool runs
`get_mcp_token(...)`	Swaps the agent token for one bound to a single MCP server, named by its Resource URI (token exchange). The new token works only at that server
`is_budget_exhausted()`	Prevents the Crew run if the agent's daily budget is spent

Next steps

Agent Registry overview — manage registrations, budgets, and capabilities
JIT Permissions — CrewAI — add just-in-time permission escalation

Standards used on this page

Plain name	Standard
Token exchange (delegation)	RFC 8693

See the standards reference for what each one covers and how LumoAuth uses it.

Install​

Example​

How it works​

Next steps​

Standards used on this page​

Install

Example

How it works

Next steps

Standards used on this page