Get the full compiled guardrail profile for an agent. For basic verification, check confirmed_settings + defaults_applied in the onboard response. Use guard_get_profile for deep inspection after update or when debugging scanner behavior. Response sections: scanner_config -- pii_level, presidio_en...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Clevername server.
Free to start. No card required.
AI agents call guard_get_profile to retrieve information from Clevername 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 guard_get_profile 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": {
"guard_get_profile": {}
}
}See the full Clevername policy for all 67 tools.
These attack patterns abuse exactly the kind of access guard_get_profile 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.
Get the full compiled guardrail profile for an agent. For basic verification, check confirmed_settings + defaults_applied in the onboard response. Use guard_get_profile for deep inspection after update or when debugging scanner behavior. Response sections: scanner_config -- pii_level, presidio_enabled, block_urls_in_output, key_interception_mode, injection_tier, ml_classifier_enabled scope -- allowed_models, allowed_tools, blocked_tools, tool_permission_level circuit_breaker -- budget_usd, spend_mtd, max_calls_per_minute, max_errors_before_pause autonomy -- high_risk_action_patterns, require_watcher compliance -- frameworks, audit_mode ("metadata"/"full_content"), retention_days defaults_applied -- every setting the system defaulted (e.g. "D7=detect_and_offer"). It is categorised as a Read tool in the Clevername MCP Server, which means it retrieves data without modifying state.
Register the Clevername MCP server in PolicyLayer and add a rule for guard_get_profile: 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 Clevername. Nothing to install.
guard_get_profile 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 guard_get_profile 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 guard_get_profile. 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.
guard_get_profile is provided by the Clevername MCP server (@clevername/clevername-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 67 Clevername 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.