pressable_run_bash_commands · Pressable MCP Server MCP

WHAT IT DOES

What pressable_run_bash_commands does on Pressable MCP Server

AI agents invoke pressable_run_bash_commands to trigger actions in Pressable MCP Server. 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 pressable_run_bash_commands needs a policy

Running arbitrary bash commands on a production WordPress site represents critical risk. An AI agent with access to this tool could execute malicious commands, exfiltrate data, install backdoors, modify site files, compromise server security, or pivot to other infrastructure.

From the tool's definition Tool name explicitly states 'run_bash_commands' and description confirms it executes 'Bash commands on a specific site'. This is arbitrary code execution on a server.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pressable_run_bash_commands Rate-limited

pressable_run_bash_commands 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": {
    "pressable_run_bash_commands": {
      "limits": [
        {
          "counter": "pressable_run_bash_commands_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 Pressable MCP Server, so you can run agents against it safely.

FAQ

Questions about pressable_run_bash_commands

What does the pressable_run_bash_commands tool do? +

Run Bash commands on a specific site. It is categorised as a Execute tool in the Pressable MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pressable_run_bash_commands? +

Register the Pressable MCP Server MCP server in PolicyLayer and add a rule for pressable_run_bash_commands: 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 Pressable MCP Server. Nothing to install.

What risk level is pressable_run_bash_commands? +

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

Can I rate-limit pressable_run_bash_commands? +

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

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

pressable_run_bash_commands is provided by the Pressable MCP Server MCP server (pcwprops/pressable-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.