AI agents invoke delegate to trigger actions in iTerm MCP. 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.
Given the iTerm MCP's stated purpose of 'allowing parallel command execution' and 'role-based access for AI orchestration,' the 'delegate' tool likely routes or assigns execution tasks. Without explicit documentation, the name suggests task delegation in a system designed for executing terminal commands.
From the tool's definition Tool named 'delegate' on iTerm MCP server that controls terminal sessions with 'command execution' capabilities; no description provided but context suggests it delegates operations within a terminal orchestration system with role-based access.
Attacks that exploit this kind of access
delegate. It is categorised as a Execute tool in the iTerm MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the iTerm MCP server in PolicyLayer and add a rule for delegate: 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 iTerm MCP. Nothing to install.
delegate 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 delegate 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 delegate. 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.
delegate is provided by the iTerm MCP server (research-developer/iterm-mcp-claude-agency). 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 →