send_admin_message · Sendbird MCP: Risk & Policy

WHAT IT DOES

What send_admin_message does on Sendbird

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

WHY IT NEEDS A POLICY

Why send_admin_message needs a policy

This tool creates new message data in a chat channel, which falls under the Write category (creates or modifies data reversibly). It is not Destructive because messages are not irreversibly deleted—they can be removed or edited.

From the tool's definition Tool 'send_admin_message' description states it can 'Inject an authoritative message into a chat channel from a specific user' and 'post system notices, automated responses, or moderation actions visible to all members.' This creates and modifies chat data…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_admin_message Rate-limited

send_admin_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": {
    "send_admin_message": {
      "limits": [
        {
          "counter": "send_admin_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 Sendbird, so you can run agents against it safely.

FAQ

Questions about send_admin_message

What does the send_admin_message tool do? +

Inject an authoritative message into a chat channel from a specific user. Used by AI agents to post system notices, automated responses, or moderation actions visible to all members. It is categorised as a Write tool in the Sendbird 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_admin_message? +

Register the Sendbird MCP server in PolicyLayer and add a rule for send_admin_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 Sendbird. Nothing to install.

What risk level is send_admin_message? +

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

Can I rate-limit send_admin_message? +

Yes. Add a rate_limit block to the send_admin_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 send_admin_message completely? +

Set action: deny in the PolicyLayer policy for send_admin_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 send_admin_message? +

send_admin_message is provided by the Sendbird MCP server (nobanks/sendbird-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.