AI agents call percept_actions 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 lists previously recorded voice command and action history. It is a read-only operation that queries historical data without creating, modifying, deleting, or executing any operations. The action history is informational data about past commands, not the execution of new commands.
From the tool's definition Tool name 'percept_actions' combined with description 'List voice command/action history' clearly indicates retrieval/querying of historical data with no modification or execution capability.
Attacks that exploit this kind of access
List voice command/action history. 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_actions: 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_actions 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_actions 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_actions. 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_actions 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 →