aip_send_message · Aip Identity MCP: Risk & Policy

WHAT IT DOES

What aip_send_message does on Aip Identity

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

WHY IT NEEDS A POLICY

Why aip_send_message needs a policy

Sending messages creates new data (message records, routing information, or communication logs) within the identity system. While encrypted and directed to specific agents, it modifies system state reversibly. This is Write rather than Execute because it does not run code or trigger external operations—it simply transmits data.

From the tool's definition The tool is called 'aip_send_message' and described as 'Send an encrypted message to another agent.' This creates/modifies data (the message record in the messaging system) in a reversible manner.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

aip_send_message Rate-limited

aip_send_message 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": {
    "aip_send_message": {
      "limits": [
        {
          "counter": "aip_send_message_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 Aip Identity, so you can run agents against it safely.

FAQ

Questions about aip_send_message

What does the aip_send_message tool do? +

Send an encrypted message to another agent. It is categorised as a Write tool in the Aip Identity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on aip_send_message? +

Register the Aip Identity MCP server in PolicyLayer and add a rule for aip_send_message: 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 Aip Identity. Nothing to install.

What risk level is aip_send_message? +

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

Can I rate-limit aip_send_message? +

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

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

aip_send_message is provided by the Aip Identity MCP server (the-nexus-guard/aip-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.