get_agent_access_matrix
Shows who can run each AI agent by listing its execute ACLs, roles, active/A2A status, run-as user, and role masking, and flags agents missing execute ACLs so deny-by-default access gaps are visible.
Instructions
Who can run each AI agent: its execute ACLs (type gen_ai_agent, falling back to the "*" wildcard rule), the roles on them (flagging roles that do not exist), whether the agent is active and exposed over A2A, its run-as user, and its role masking (sys_agent_access_role_configuration). Agents with no execute ACL of their own are flagged, because Brazil makes AI agent access deny-by-default. Read-only.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "get_agent_access_matrix"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Agent name contains | |
| limit | No | Max agents (default 50, max 300) | |
| gaps_only | No | Only agents with a gap: wildcard or no execute ACL, open to any signed-in user, or missing roles | |
| active_only | No | Only active agents (default false) |