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, presidi...
Bulk/mass operation — affects multiple targets
Part of the Clevername MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
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.
tools:
guard_get_profile:
rules:
- action: allowSee the full Clevername policy for all 67 tools.
Agents calling read-class tools like guard_get_profile have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
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.
Add a rule in your Intercept YAML policy under the tools section for guard_get_profile. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Clevername MCP server.
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 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 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). 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