AI agents invoke send_command to trigger actions in Interactive Terminal MCP. 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.
The server's purpose is to run arbitrary terminal commands in persistent sessions. 'send_command' almost certainly sends input/commands to an active terminal session (SSH, REPL, debugger, etc.), which constitutes arbitrary code/command execution. The blast radius is critical — an AI agent could run any shell command, escalate privileges, exfiltrate data, or destroy systems.
From the tool's definition Tool name 'send_command' on a server described as providing 'stateful, interactive terminal access' to 'spawn and maintain persistent processes like SSH sessions, debuggers, and REPLs with continuous input/output interaction across commands'.
Documented attack patterns abuse exactly the kind of access send_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Interactive Terminal MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for send_command:
{
"version": "1",
"default": "deny",
"tools": {
"send_command": {
"limits": [
{
"counter": "send_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}send_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.
Free to start. No card required.
send_command. It is categorised as a Execute tool in the Interactive Terminal MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Interactive Terminal MCP server in PolicyLayer and add a rule for send_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 Interactive Terminal MCP. Nothing to install.
send_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the send_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.
Set action: deny in the PolicyLayer policy for send_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.
send_command is provided by the Interactive Terminal MCP server (wangyihang/interactive-terminal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Interactive Terminal MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Interactive Terminal MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.