Agent Guardrail
Action-level policy enforcement for AI agents — control what agents DO, not just what they say.
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение
Что умеет
- Evaluate Action: Evaluate whether an agent action is allowed by the guardrail policy. Call this BEFORE executing any tool, shell command, or HTTP request.
- Register Agent: Register a new agent with the guardrail system. Must be called before evaluate_action.
- List Agents: List all agents currently registered in the guardrail system. Shows active and killed agents. Returns: Array of agent records with fields: id, name, framework, description, status, create
Какие данные видит
Нужен ли аккаунт
Не нужен: сервер работает без входа
Action-level policy enforcement for AI agents — control what agents DO, not just what they say. Evaluate actions against configurable security policies before execution.
Список инструментов сервера (6)
Технические названия из tools/list. Нужны только разработчикам.
| evaluate_action | Evaluate whether an agent action is allowed by the guardrail policy. Call this BEFORE executing any tool, shell command, or HTTP request. |
| register_agent | Register a new agent with the guardrail system. Must be called before evaluate_action. |
| list_agents | List all agents currently registered in the guardrail system. Shows active and killed agents. Returns: Array of agent records with fields: id, name, framework, description, status, created_at. |
| get_stats | Retrieve aggregate statistics from the guardrail system including evaluation counts, policy data, and agent metrics. Returns: Statistics object with fields: total_evaluations, allowed_count, denied_count, agent_count, policy_count. |
| kill_agent | Emergency kill-switch: immediately block ALL actions for an agent. Use when an agent is misbehaving or compromised. |
| unkill_agent | Re-enable a previously killed agent, restoring its ability to have actions evaluated. |