AI agents invoke focus_session to trigger actions in Iterm2. 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.
Focusing a session is an external operation that manipulates the state of the iTerm2 application (bringing a window/tab/pane to the foreground). It doesn't read data, write/modify persistent data, delete anything, or involve finances. It executes a UI action with minimal blast radius — at worst it causes an unexpected window to appear in the foreground, which is trivially reversible by the user.
From the tool's definition 'Bring a session to the foreground' — triggers an external UI operation on the iTerm2 application, changing window/focus state
Attacks that exploit this kind of access
Bring a session to the foreground. It is categorised as a Execute tool in the Iterm2 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Iterm2 MCP server in PolicyLayer and add a rule for focus_session: 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.
focus_session 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 focus_session 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 focus_session. 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.
focus_session 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 →