AI agents call percept_security_log to retrieve information from Percept without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays historical security event records (blocked attempts, unauthorized access events). It has no side effects, does not execute code, modify data, delete records, or move money. The verb 'View' explicitly indicates read-only access.
From the tool's definition Tool name 'percept_security_log' and description 'View security log — blocked attempts and unauthorized access events' indicate retrieval of log data with no modification capability.
Attacks that exploit this kind of access
View security log — blocked attempts and unauthorized access events. It is categorised as a Read tool in the Percept MCP Server, which means it retrieves data without modifying state.
Register the Percept MCP server in PolicyLayer and add a rule for percept_security_log: 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 Percept. Nothing to install.
percept_security_log 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 percept_security_log 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 percept_security_log. 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.
percept_security_log is provided by the Percept MCP server (getpercept). 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 →