session_interrupt · Claude Code MCP: Risk & Policy

WHAT IT DOES

What session_interrupt does on Claude Code

AI agents invoke session_interrupt to trigger actions in Claude Code. 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_interrupt needs a policy

This tool sends a signal (Ctrl-C/SIGINT) to an active session to interrupt/abort whatever is currently running. It is an external operation that triggers a side effect (aborting a running process) rather than merely reading data or writing/deleting persistent data. Misuse could abort important in-progress operations, hence medium severity.

From the tool's definition Send Ctrl-C to the named session to abort the current operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

session_interrupt Rate-limited

session_interrupt 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_interrupt": {
      "limits": [
        {
          "counter": "session_interrupt_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 Claude Code, so you can run agents against it safely.

FAQ

Questions about session_interrupt

What does the session_interrupt tool do? +

Send Ctrl-C to the named session to abort the current operation. It is categorised as a Execute tool in the Claude Code 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_interrupt? +

Register the Claude Code MCP server in PolicyLayer and add a rule for session_interrupt: 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 Claude Code. Nothing to install.

What risk level is session_interrupt? +

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

Can I rate-limit session_interrupt? +

Yes. Add a rate_limit block to the session_interrupt 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_interrupt completely? +

Set action: deny in the PolicyLayer policy for session_interrupt. 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_interrupt? +

session_interrupt is provided by the Claude Code MCP server (joschi655/claude-code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.