Runs a read-oriented function call inside the selected LocalWP site
AI agents invoke wp_call_function 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.
Despite being described as 'read-oriented', this tool executes arbitrary PHP/WordPress function calls inside a live site. The actual execution of code in a running WordPress environment can have side effects depending on the function called. 'Read-oriented' is a stated intent, not a technical constraint, so the true category is Execute.
From the tool's definition 'Runs a read-oriented function call inside the selected LocalWP site' — executes code within the WordPress environment
Attacks that exploit this kind of access
Runs a read-oriented function call inside the selected LocalWP site. 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 wp_call_function: 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.
wp_call_function 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 wp_call_function 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 wp_call_function. 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.
wp_call_function 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 →