safety_check
AI agents call safety_check to retrieve information from Agent Safety without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the server's stated purpose (detecting prompt injection, scanning outputs, enforcing budgets, creating audit trails) and the naming pattern of sibling tools, 'safety_check' most likely performs a read-only security scan or validation check. It would retrieve or analyze data to detect safety violations without creating side effects.
From the tool's definition Tool name 'safety_check' suggests a read-only validation/scanning operation. No description provided. Sibling tools on the server (injection_check, injection_scan, cost_guard_check) are all read-only safety validators that detect problems without modifying…
Attacks that exploit this kind of access
safety_check. It is categorised as a Read tool in the Agent Safety MCP Server, which means it retrieves data without modifying state.
Register the Agent Safety MCP server in PolicyLayer and add a rule for safety_check: 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 Agent Safety. Nothing to install.
safety_check 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_check 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_check. 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_check is provided by the Agent Safety MCP server (luciferforge/agent-safety-mcp). 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 →