Run a system tool
AI agents invoke woo_system_tools_run to trigger actions in Woocommerce. 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 is clearly an Execute category tool because it runs system tools whose effects depend entirely on what arguments are provided. The vague description 'Run a system tool' suggests broad capability to invoke arbitrary system operations.
From the tool's definition Tool description states 'Run a system tool' which indicates execution of arbitrary system-level operations.
Attacks that exploit this kind of access
Run a system tool. It is categorised as a Execute tool in the Woocommerce MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Woocommerce MCP server in PolicyLayer and add a rule for woo_system_tools_run: 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 Woocommerce. Nothing to install.
woo_system_tools_run 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 woo_system_tools_run 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 woo_system_tools_run. 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.
woo_system_tools_run is provided by the Woocommerce MCP server (@lockon0927/woocommerce-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 →