AI agents call get_screen to retrieve information from Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns previously captured terminal output without modifying, executing, or deleting anything. It is a passive query operation similar to viewing a log or cache. The blast radius is minimal—an agent can only retrieve information that was already captured, with no ability to affect system state, execute commands, or access data beyond what is already buffered in memory.
From the tool's definition Tool name 'get_screen' and description 'Return the latest terminal output kept in memory' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Return the latest terminal output kept in memory. It is categorised as a Read tool in the Ssh MCP Server, which means it retrieves data without modifying state.
Register the Ssh MCP server in PolicyLayer and add a rule for get_screen: 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.
get_screen is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_screen 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 get_screen. 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.
get_screen 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 →