terminal_exec · Global MCP Manager MCP: Risk & Policy

WHAT IT DOES

What terminal_exec does on Global MCP Manager

AI agents invoke terminal_exec to trigger actions in Global MCP Manager. 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 terminal_exec needs a policy

The tool name 'terminal_exec' strongly implies executing terminal/shell commands. The server description explicitly states it enables 'executing terminal commands' across multiple environments (local, SSH, remote).

From the tool's definition Tool name 'terminal_exec' on a server described as 'Enables executing terminal commands' across local, SSH, and GitHub contexts

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

terminal_exec Rate-limited

terminal_exec 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": {
    "terminal_exec": {
      "limits": [
        {
          "counter": "terminal_exec_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 Global MCP Manager, so you can run agents against it safely.

FAQ

Questions about terminal_exec

What does the terminal_exec tool do? +

terminal_exec. It is categorised as a Execute tool in the Global MCP Manager MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on terminal_exec? +

Register the Global MCP Manager MCP server in PolicyLayer and add a rule for terminal_exec: 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 Global MCP Manager. Nothing to install.

What risk level is terminal_exec? +

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

Can I rate-limit terminal_exec? +

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

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

terminal_exec is provided by the Global MCP Manager MCP server (mamprimauto/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.