Action governance for AI agents — protective checks before execution. Use this to verify tool calls, SQL queries, file writes, shell commands, web searches, and inter-agent messages are safe before you act. Returns a clear allow / approve / block signal so you don
AI agents call shrike_scan to retrieve information from Shrike Security without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a security scanning/validation tool that reads and analyzes potential actions for safety compliance. It has no ability to modify data, execute commands, delete resources, or move money. It only produces a governance decision (allow/approve/block) based on inspection.
From the tool's definition The tool description states it performs 'protective checks before execution' and 'returns a clear allow / approve / block signal' — it analyzes and reports on safety without executing, modifying, or deleting anything.
Attacks that exploit this kind of access
Action governance for AI agents — protective checks before execution. Use this to verify tool calls, SQL queries, file writes, shell commands, web searches, and inter-agent messages are safe before you act. Returns a clear allow / approve / block signal so you don. It is categorised as a Read tool in the Shrike Security MCP Server, which means it retrieves data without modifying state.
Register the Shrike Security MCP server in PolicyLayer and add a rule for shrike_scan: 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 Shrike Security. Nothing to install.
shrike_scan 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 shrike_scan 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 shrike_scan. 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.
shrike_scan is provided by the Shrike Security MCP server (shrike-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
shrike_scan is one line of Shrike Security's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →