session_run · It2 MCP: Risk & Policy

WHAT IT DOES

What session_run does on It2mcp

AI agents invoke session_run 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.

WHY IT NEEDS A POLICY

Why session_run needs a policy

This tool executes shell commands in iTerm2 sessions with unrestricted argument capability. An AI agent could execute destructive commands (rm -rf /), exfiltrate data, modify system configuration, or pivot to other systems. The blast radius is terminal-wide system compromise. While the server includes a security model with session tagging and permissions, the tool itself has Execute semantics.

From the tool's definition Tool description states: 'Execute a command in an iTerm2 session (sends text + Enter)'. This directly runs arbitrary commands in a terminal session with effects determined by the command argument.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

session_run Rate-limited

session_run stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "session_run": {
      "limits": [
        {
          "counter": "session_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches It2mcp, so you can run agents against it safely.

FAQ

Questions about session_run

What does the session_run tool do? +

Execute a command in an iTerm2 session (sends text + 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.

How do I enforce a policy on session_run? +

Register the It2 MCP server in PolicyLayer and add a rule for session_run: 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.

What risk level is session_run? +

session_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit session_run? +

Yes. Add a rate_limit block to the session_run 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.

How do I block session_run completely? +

Set action: deny in the PolicyLayer policy for session_run. 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.

What MCP server provides session_run? +

session_run 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.