Stops the selected LocalWP site and all of its services.
AI agents invoke stop_local_site to trigger actions in LocalWP MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes an external operation (stopping services) rather than merely reading or writing data. While not destructive (services can be restarted), it interrupts running operations and affects system state in a way that depends on the argument (which site is selected).
From the tool's definition Tool explicitly 'Stops the selected LocalWP site and all of its services' - a direct action that triggers external operations (service shutdown) with effects dependent on which site is targeted.
Attacks that exploit this kind of access
Stops the selected LocalWP site and all of its services. It is categorised as a Execute tool in the LocalWP MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LocalWP MCP server in PolicyLayer and add a rule for stop_local_site: 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 LocalWP MCP. Nothing to install.
stop_local_site is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop_local_site 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 stop_local_site. 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.
stop_local_site is provided by the LocalWP MCP server (kazimshah39/localwp-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 →