AI agents call get_variable to retrieve information from Iterm2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'get_variable' indicates a query or retrieval operation typical of Read category tools. Although the description is empty (lowering confidence slightly), the naming convention and context of sibling Read tools (list_sessions, get_active_session, read_screen) strongly suggest this retrieves data without side effects.
From the tool's definition Tool name 'get_variable' suggests retrieval of a variable value with no modification capability. Sibling tools include 'read_screen' and 'get_cursor_position' which are clearly Read operations, supporting this classification.
Attacks that exploit this kind of access
get_variable. It is categorised as a Read tool in the Iterm2 MCP Server, which means it retrieves data without modifying state.
Register the Iterm2 MCP server in PolicyLayer and add a rule for get_variable: 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 Iterm2. Nothing to install.
get_variable 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_variable 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_variable. 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_variable is provided by the Iterm2 MCP server (lorencarvalho/iterm2-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 →