terminal · Terminal MCP Server MCP: Risk & Policy

WHAT IT DOES

What terminal does on Terminal MCP Server

AI agents invoke terminal to trigger actions in Terminal 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 terminal needs a policy

Shell command execution is a quintessential Execute category risk. An AI agent given access to this tool can run any command the underlying process permits—including data exfiltration, system reconnaissance, lateral movement, malware deployment, or destructive operations. While the server provides 'timeout protection,' this does not constrain what commands can be executed, only their duration.

From the tool's definition Tool description states 'Run terminal commands and return the output.' Combined with server description 'Enables execution of shell commands through a terminal tool,' this tool directly executes arbitrary shell commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

terminal Rate-limited

terminal 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": {
      "limits": [
        {
          "counter": "terminal_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 Terminal MCP Server, so you can run agents against it safely.

FAQ

Questions about terminal

What does the terminal tool do? +

Run terminal commands and return the output. It is categorised as a Execute tool in the Terminal 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 terminal? +

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

What risk level is terminal? +

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

Can I rate-limit terminal? +

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

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

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