v1.0.2: Get terminal
AI agents call get_live_output to retrieve information from Ai Mcp Terminal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves live output from a terminal session without executing commands, modifying state, or triggering side effects. The 'get' prefix and read-only nature of retrieving output places it in the Read category. Severity is low because viewing terminal output poses minimal risk—the dangerous operations (command execution, deletion) are handled by sibling tools like 'execute_command' and 'execute_batch'.
From the tool's definition Tool name is 'get_live_output' and description states 'Get terminal', indicating retrieval of terminal output with no modification or execution capability.
Attacks that exploit this kind of access
v1.0.2: Get terminal. It is categorised as a Read tool in the Ai Mcp Terminal MCP Server, which means it retrieves data without modifying state.
Register the Ai Mcp Terminal MCP server in PolicyLayer and add a rule for get_live_output: 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 Ai Mcp Terminal. Nothing to install.
get_live_output 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_live_output 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_live_output. 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_live_output is provided by the Ai Mcp Terminal MCP server (kanniganfan/ai-mcp-terminal). 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 →