share_command · Claude IPC MCP: Risk & Policy

WHAT IT DOES

What share_command does on Claude IPC MCP

AI agents invoke share_command to trigger actions in Claude IPC 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.

WHY IT NEEDS A POLICY

Why share_command needs a policy

This tool runs commands whose effects depend on the arguments provided by the AI agent. While the immediate output is shared rather than directly modifying local state, command execution is inherently an Execute-category operation with potentially high blast radius if misused (could execute rm, SQL injections, etc.).

From the tool's definition Tool explicitly states it 'Execute[s] a command' and shares output with another instance. The verb 'execute' combined with 'command' indicates arbitrary code/command execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

share_command Rate-limited

share_command 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": {
    "share_command": {
      "limits": [
        {
          "counter": "share_command_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 IPC MCP, so you can run agents against it safely.

FAQ

Questions about share_command

What does the share_command tool do? +

Execute a command and share output with another instance. It is categorised as a Execute tool in the Claude IPC MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on share_command? +

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

What risk level is share_command? +

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

Can I rate-limit share_command? +

Yes. Add a rate_limit block to the share_command 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 share_command completely? +

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

share_command is provided by the Claude IPC MCP server (jdez427/claude-ipc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.