AI agents invoke send_text to trigger actions in Ssh. 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 raw text to an interactive shell is equivalent to executing arbitrary commands. The blast radius is high because an AI agent could send any shell command over SSH, potentially modifying or destroying data on a remote system. The SSH context and 'interactive shell' wording make this clearly Execute-level at minimum, with no bounds on what can be sent.
From the tool's definition Send raw text to the current interactive shell or menu
Attacks that exploit this kind of access
Send raw text to the current interactive shell or menu. It is categorised as a Execute tool in the Ssh MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ssh 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 Ssh. 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 Ssh MCP server (sc-ml-cmd/ssh-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 →