Check when system appropriately refuses potentially harmful requests
AI agents call safety.evaluate_refusal_appropriateness to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs an assessment or audit of refusal decisions—a read-only introspection capability. It retrieves or analyzes information about whether the system has correctly refused a harmful request, with no side effects, data modification, code execution, or destruction.
From the tool's definition Tool name 'evaluate_refusal_appropriateness' and description 'Check when system appropriately refuses potentially harmful requests' indicate inspection/analysis of refusal behavior without modifying, executing, or destroying anything.
Attacks that exploit this kind of access
Check when system appropriately refuses potentially harmful requests. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for safety.evaluate_refusal_appropriateness: 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 ContextForge MCP Gateway. Nothing to install.
safety.evaluate_refusal_appropriateness 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 safety.evaluate_refusal_appropriateness 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 safety.evaluate_refusal_appropriateness. 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.
safety.evaluate_refusal_appropriateness is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →