ht_execute_command · HT MCP Server MCP: Risk & Policy

WHAT IT DOES

What ht_execute_command does on HT MCP Server

AI agents invoke ht_execute_command to trigger actions in HT 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 ht_execute_command needs a policy

This tool allows running arbitrary shell commands through an interactive terminal session. While not inherently destructive, it enables execution of operations with wide-ranging side effects (file manipulation, system configuration, installing software, etc.).

From the tool's definition Tool description explicitly states it 'Execute[s] a command in the terminal and return[s] the output.' This is a direct execution interface to arbitrary terminal commands whose effects depend on the command argument.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ht_execute_command Rate-limited

ht_execute_command 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": {
    "ht_execute_command": {
      "limits": [
        {
          "counter": "ht_execute_command_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 HT MCP Server, so you can run agents against it safely.

FAQ

Questions about ht_execute_command

What does the ht_execute_command tool do? +

Execute a command in the terminal and return the output. This combines sending the command + Enter key + taking a snapshot. It is categorised as a Execute tool in the HT 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 ht_execute_command? +

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

What risk level is ht_execute_command? +

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

Can I rate-limit ht_execute_command? +

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

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

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