Compute 0-100 risk score for any tool + input combination. 0=minimal risk (read-only), 100=critical (payment/irreversible). Detects secrets, injection attempts, high-value amounts. Use before deciding whether to proceed with a tool call.
Part of the Agentguard server.
Free to start. No card required.
AI agents may call tool_risk_score to permanently remove or destroy resources in Agentguard. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call tool_risk_score in a loop, permanently destroying resources in Agentguard. There is no undo for destructive operations. PolicyLayer 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.
{
"version": "1",
"default": "deny",
"hide": [
"tool_risk_score"
]
}See the full Agentguard policy for all 24 tools.
These attack patterns abuse exactly the kind of access tool_risk_score gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Compute 0-100 risk score for any tool + input combination. 0=minimal risk (read-only), 100=critical (payment/irreversible). Detects secrets, injection attempts, high-value amounts. Use before deciding whether to proceed with a tool call.. It is categorised as a Destructive tool in the Agentguard MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agentguard MCP server in PolicyLayer and add a rule for tool_risk_score: 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 Agentguard. Nothing to install.
tool_risk_score 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 tool_risk_score 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 tool_risk_score. 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.
tool_risk_score is provided by the Agentguard MCP server (https://feedoracle.io/guard-oracle/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 24 Agentguard 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.