AI agents call search_actions to retrieve information from Unifi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/list operation that retrieves information about available actions without modifying, executing, or deleting anything. It is purely informational and returns data for downstream use. While the broader server context includes Execute and Write capabilities (execute_action, client_action, device_action), this specific tool is a safe read operation.
From the tool's definition Tool description states it 'Search[es] the UniFi action catalog and return[s] action IDs' — a read-only query operation with no side effects. The tool retrieves and lists available actions but does not execute them (execution is delegated to execute_action).
Attacks that exploit this kind of access
Search the UniFi action catalog and return action IDs that can be executed via execute_action. It is categorised as a Read tool in the Unifi MCP Server, which means it retrieves data without modifying state.
Register the Unifi MCP server in PolicyLayer and add a rule for search_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 Unifi. Nothing to install.
search_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 search_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 search_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.
search_actions is provided by the Unifi MCP server (pproenca/unifi-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 →