Manage a scenario: update its fields, delete it, or toggle its active state. IMPORTANT: Deletion is permanent and irreversible. When action="delete", you MUST first call this tool WITHOUT confirm=true. The tool will return a confirmation prompt listing the scenario to be deleted. Show this to th...
Part of the Invarium MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call invarium_manage_scenario to permanently remove or destroy resources in Invarium. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call invarium_manage_scenario in a loop, permanently destroying resources in Invarium. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
invarium_manage_scenario:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Invarium policy for all 19 tools.
Agents calling destructive-class tools like invarium_manage_scenario have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
invarium_manage_scenario is one of the critical-risk operations in Invarium. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
Manage a scenario: update its fields, delete it, or toggle its active state. IMPORTANT: Deletion is permanent and irreversible. When action="delete", you MUST first call this tool WITHOUT confirm=true. The tool will return a confirmation prompt listing the scenario to be deleted. Show this to the user and only re-call with confirm=true after they explicitly approve. NEVER set confirm=true on the first call. NEVER delete multiple scenarios in a loop without showing the user the full list and getting one explicit confirmation for the batch. Args: scenario_id: ID of the scenario to manage. action: Operation to perform — "update", "delete", or "toggle". name: New name for the scenario (update only). description: New description for the scenario (update only). expected_behavior: New expected behavior text (update only). tags: JSON array string of tags, e.g. '["auth", "edge-case"]' (update only). confirm: Required for delete — must be true to execute deletion. First call without confirm to get a confirmation prompt. Returns: A confirmation string on success, or an error message on failure.. It is categorised as a Destructive tool in the Invarium MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for invarium_manage_scenario. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Invarium MCP server.
invarium_manage_scenario is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the invarium_manage_scenario rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for invarium_manage_scenario. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
invarium_manage_scenario is provided by the Invarium MCP server (invarium-ai/invarium). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept