AI agents invoke send_text to trigger actions in PiloTY. 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.
Given the server context (persistent interactive terminal) and sibling tools (send_line, send_signal, send_control), send_text almost certainly sends arbitrary text input to a terminal session. This constitutes executing arbitrary shell commands or inputs, which has critical blast radius as it can run any command on the underlying system.
From the tool's definition Tool name 'send_text' on a server described as providing 'a persistent, interactive terminal, enabling long-running commands, log monitoring, and stateful shell interactions across tool calls.' Sibling tools include send_line, send_signal, send_control,…
Documented attack patterns abuse exactly the kind of access send_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PiloTY, and nothing reaches the server without passing your rules. This is the rule we recommend for send_text:
{
"version": "1",
"default": "deny",
"tools": {
"send_text": {
"limits": [
{
"counter": "send_text_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}send_text 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_text. It is categorised as a Execute tool in the PiloTY MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PiloTY MCP server in PolicyLayer and add a rule for send_text: 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 PiloTY. Nothing to install.
send_text 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_text 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_text. 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_text is provided by the PiloTY MCP server (yiwenlu66/piloty). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 PiloTY tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 PiloTY tools catalogued and risk-classified — across an index of 42,500+ MCP servers.