AI agents use session_set_name to create or update resources in It2mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your It2mcp environment.
This is a reversible write operation that modifies iTerm2 session metadata (the session name). It does not execute arbitrary code, delete data, or create financial obligations. While it is an Write action affecting application state, the scope is narrowly limited to renaming a session, which is a low-risk operation with minimal blast radius even if misused by an agent.
From the tool's definition Tool performs 'Set the name of an iTerm2 session' — a metadata modification that creates or updates a session property without deleting data or executing terminal commands.
Attacks that exploit this kind of access
Set the name of an iTerm2 session. It is categorised as a Write tool in the It2mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the It2 MCP server in PolicyLayer and add a rule for session_set_name: 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 It2mcp. Nothing to install.
session_set_name is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the session_set_name 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 session_set_name. 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.
session_set_name is provided by the It2 MCP server (urjitbhatia/it2mcp). 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 →