wp_eval · Wp Cli MCP: Risk & Policy

WHAT IT DOES

What wp_eval does on Wp Cli

AI agents invoke wp_eval to trigger actions in Wp Cli. 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.

WHY IT NEEDS A POLICY

Why wp_eval needs a policy

This tool allows execution of arbitrary code within a live WordPress environment with full database and hook access. An AI agent misuse could lead to data exfiltration, malware injection, unauthorized database modifications, privilege escalation, or system compromise.

From the tool's definition Tool executes arbitrary PHP code in the WordPress environment with access to all WordPress functions, hooks, and the database. Description explicitly states: Execute arbitrary PHP code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wp_eval Rate-limited

wp_eval stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "wp_eval": {
      "limits": [
        {
          "counter": "wp_eval_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Wp Cli, so you can run agents against it safely.

FAQ

Questions about wp_eval

What does the wp_eval tool do? +

Execute arbitrary PHP code in the WordPress environment. Has access to all WordPress functions, hooks, and the database. Use for custom queries, data manipulation, or anything not covered by other tools. It is categorised as a Execute tool in the Wp Cli MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wp_eval? +

Register the Wp Cli MCP server in PolicyLayer and add a rule for wp_eval: 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 Wp Cli. Nothing to install.

What risk level is wp_eval? +

wp_eval is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit wp_eval? +

Yes. Add a rate_limit block to the wp_eval 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.

How do I block wp_eval completely? +

Set action: deny in the PolicyLayer policy for wp_eval. 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.

What MCP server provides wp_eval? +

wp_eval is provided by the Wp Cli MCP server (mvtandas/wp-cli-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.