send · Claude IPC MCP: Risk & Policy

WHAT IT DOES

What send does on Claude IPC MCP

AI agents use send to create or update resources in Claude IPC MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude IPC MCP environment.

WHY IT NEEDS A POLICY

Why send needs a policy

Sending a message is a Write operation: it creates a new message and delivers it to another instance. It is reversible in the sense that messages can be ignored, but the act of sending cannot be undone. There is no indication of code execution, deletion, or financial action. Severity is medium because messages sent to other AI instances could trigger further downstream actions depending on the recipient's behavior.

From the tool's definition "Send a message to another Claude instance" — creates and transmits a message to another process

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send Rate-limited

send stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send": {
      "limits": [
        {
          "counter": "send_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 send

What does the send tool do? +

Send a message to another Claude instance. It is categorised as a Write tool in the Claude IPC MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send? +

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

What risk level is send? +

send is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send? +

Yes. Add a rate_limit block to the 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.

How do I block send completely? +

Set action: deny in the PolicyLayer policy for 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.

What MCP server provides send? +

send 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.