send_items · Messaging MCP: Risk & Policy

WHAT IT DOES

What send_items does on Messaging

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

WHY IT NEEDS A POLICY

Why send_items needs a policy

This tool performs a Write operation: it creates and sends message content to external recipients, resulting in reversible side effects (messages can be retracted or deleted, and recipients' inboxes are modified but the fundamental data structures remain intact). It does not permanently destroy data (Destructive), move money (Financial), or execute arbitrary code (Execute).

From the tool's definition send_items sends 'structured items' as RCS cards, which creates and transmits data. The tool modifies the state of the messaging system by composing and delivering content to recipients.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_items Rate-limited

send_items 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_items": {
      "limits": [
        {
          "counter": "send_items_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 Messaging, so you can run agents against it safely.

FAQ

Questions about send_items

What does the send_items tool do? +

Send structured items (products, events, sessions) as rich RCS cards. It is categorised as a Write tool in the Messaging 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_items? +

Register the Messaging MCP server in PolicyLayer and add a rule for send_items: 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 Messaging. Nothing to install.

What risk level is send_items? +

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

Can I rate-limit send_items? +

Yes. Add a rate_limit block to the send_items 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_items completely? +

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

send_items is provided by the Messaging MCP server (@sure-shot/mcp-server-messaging). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.