Activates a plugin
AI agents invoke activate_plugin to trigger actions in mcp-wordpress-instaWP. 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.
Activating a plugin causes PHP code to execute on the WordPress server. A malicious or vulnerable plugin could compromise the entire site. This is an Execute-category action with high severity because the blast radius includes full site compromise, data exfiltration, or backdoor installation depending on which plugin is activated.
From the tool's definition 'Activates a plugin' — enabling a plugin runs its code within the WordPress environment, triggering external operations and executing arbitrary plugin logic.
Attacks that exploit this kind of access
Activates a plugin. It is categorised as a Execute tool in the mcp-wordpress-instaWP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the mcp-wordpress-instaWP MCP server in PolicyLayer and add a rule for activate_plugin: 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 mcp-wordpress-instaWP. Nothing to install.
activate_plugin 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 activate_plugin 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 activate_plugin. 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.
activate_plugin is provided by the mcp-wordpress-instaWP MCP server (pace8/mcp-wordpress). 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 →