AI agents invoke session_send to trigger actions in It2mcp. 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.
Sending text to a terminal session can stage arbitrary commands for execution. Even without pressing Enter, the text is placed in an active terminal buffer and could be completed or executed by subsequent actions. The blast radius is high as it can inject commands into any active terminal session, potentially affecting files, processes, and system state.
From the tool's definition "Send text to an iTerm2 session" — sends arbitrary text/commands to a terminal session
Attacks that exploit this kind of access
Send text to an iTerm2 session without pressing Enter. It is categorised as a Execute tool in the It2mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the It2 MCP server in PolicyLayer and add a rule for session_send: 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_send 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 session_send 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_send. 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_send 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 →