start_wp_shell

THE RISK

High Risk

Why start_wp_shell needs a policy

This tool directly executes arbitrary PHP code within a live WordPress application. While framed as a penetration testing utility, providing an interactive shell that runs code in the target's context is the definition of Execute capability. The ability to run arbitrary commands in a WordPress environment gives an AI agent unrestricted control over the target system, making this critical severity.

From the tool's definition Opens an interactive PHP shell (REPL) within WordPress context—enables arbitrary code execution in the target application environment.

Documented attack patterns abuse exactly the kind of access start_wp_shell gives an agent:

POLICY

How to control start_wp_shell

PolicyLayer is an MCP gateway — it sits between your AI agents and Pentester-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for start_wp_shell:

policy.json

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

start_wp_shell 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.

Create a free account and register Pentester-MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Pentester-MCP tools

Execute dnscat_client dnscat_client Execute execute_weevely_module execute_weevely_module Execute identify_hash identify_hash Execute john_prepare john_prepare Execute launch_xsser_gui Launches the graphical user interface (GTK) for XSSer. Execute objection_explore objection_explore Execute run_403bypasser run_403bypasser Execute run_addcomputer run_addcomputer

All 337 Pentester-MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

Govern code and CI agents → Branch allowlists, approval on merges, and rate caps on the build and pipeline tools agents trigger.
High-risk tools in Pentester-MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →
PolicyLayer vs alternatives → How deterministic, per-call MCP policy compares with gateways, identity layers, and authorisation platforms.

FAQ

Questions about start_wp_shell

What does the start_wp_shell tool do? +

Open an interactive PHP shell (REPL) within the context of the WordPress environment. It is categorised as a Execute tool in the Pentester-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_wp_shell? +

Register the Pentester- MCP server in PolicyLayer and add a rule for start_wp_shell: 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 Pentester-MCP. Nothing to install.

What risk level is start_wp_shell? +

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

Can I rate-limit start_wp_shell? +

Yes. Add a rate_limit block to the start_wp_shell 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 start_wp_shell completely? +

Set action: deny in the PolicyLayer policy for start_wp_shell. 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 start_wp_shell? +

start_wp_shell is provided by the Pentester- MCP server (halilkirazkaya/pentester-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Pentester-MCP tool call.

Start from Pentester-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →