vizier_screen_action
Screen AI agent actions before execution by checking policy, DLP, and loop constraints, then return ALLOW, REVIEW, or BLOCK with an auditable receipt.
Instructions
Screen and authorize a proposed AI agent action before execution. Evaluates deterministic policy constraints, DLP leakage, loop prevention, and returns an ALLOW / REVIEW / BLOCK decision with an auditable cryptographic receipt.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"action_type": "<action_type>",
"target": "<target>"
},
"name": "vizier_screen_action"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | Exact target resource URI or identifier (e.g. 'mcp://github/create_issue', 'stripe://charges', 'bash://rm', 'https://api.example.com'). | |
| agent_id | No | Identifier of the agent requesting action. | claude |
| parameters | No | Arguments or payload of the proposed action. | |
| action_type | Yes | Category of action: 'tool_call', 'shell_command', 'payment', 'database_write', 'external_api', 'file_modification', or 'mcp_proxy'. | |
| principal_id | No | Identifier of the human operator or principal. | operator |