Retrieve the latest static audit results for your agent. Shows the Agent Readiness Score (ARS), per-category breakdown, and findings grouped by severity (critical, high, medium, low) with recommended fixes. The audit runs automatically when you upload a blueprint. WHEN TO USE: Phase 1, Step 4 — r...
Part of the Invarium server.
Free to start. No card required.
AI agents call invarium_get_audit to retrieve information from Invarium without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though invarium_get_audit only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"invarium_get_audit": {}
}
}See the full Invarium policy for all 19 tools.
These attack patterns abuse exactly the kind of access invarium_get_audit gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Retrieve the latest static audit results for your agent. Shows the Agent Readiness Score (ARS), per-category breakdown, and findings grouped by severity (critical, high, medium, low) with recommended fixes. The audit runs automatically when you upload a blueprint. WHEN TO USE: Phase 1, Step 4 — right after invarium_upload_blueprint to get the server-side audit score. Also useful anytime the user wants to review their agent's security posture. AFTER THIS: Present the findings and proactively suggest targeted test scenarios based on the audit weaknesses. Ask: "Based on these audit findings, would you like me to suggest test scenarios to validate your agent's weak areas?" Args: agent_name: Name of the agent to retrieve audit results for.. It is categorised as a Read tool in the Invarium MCP Server, which means it retrieves data without modifying state.
Register the Invarium MCP server in PolicyLayer and add a rule for invarium_get_audit: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Invarium. Nothing to install.
invarium_get_audit is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the invarium_get_audit rule in your PolicyLayer 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 PolicyLayer policy for invarium_get_audit. 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_get_audit is provided by the Invarium MCP server (invarium-ai/invarium). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 Invarium tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.