Send keys to an HT session. Keys can include text and special keys like
AI agents invoke ht_send_keys 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.
Sending keystrokes to an interactive terminal session is equivalent to executing arbitrary commands or actions within that session. The blast radius is high because an AI agent could send any sequence of keys, including destructive shell commands, to a live terminal session.
From the tool's definition 'Send keys to an HT session. Keys can include text and special keys' — sends arbitrary keystrokes to a running terminal session, enabling execution of any command or interaction with any terminal application
Attacks that exploit this kind of access
Send keys to an HT session. Keys can include text and special keys like. 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.
Register the HT MCP Server MCP server in PolicyLayer and add a rule for ht_send_keys: 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.
ht_send_keys 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 ht_send_keys 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 ht_send_keys. 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.
ht_send_keys 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →