sendook_send_message · Sendook MCP: Risk & Policy

WHAT IT DOES

What sendook_send_message does on Sendook

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

WHY IT NEEDS A POLICY

Why sendook_send_message needs a policy

This tool creates and sends email messages, which is a reversible write operation (emails can be deleted or unsent in most systems, and the action modifies state without permanent destruction). Severity is high due to potential for abuse—an AI agent with unchecked access could spam, impersonate, or conduct phishing campaigns.

From the tool's definition Tool name 'sendook_send_message' indicates message creation/transmission. Server description states the platform 'Enables AI agents to send and receive emails' with explicit send capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sendook_send_message Rate-limited

sendook_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": {
    "sendook_send_message": {
      "limits": [
        {
          "counter": "sendook_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 Sendook, so you can run agents against it safely.

FAQ

Questions about sendook_send_message

What does the sendook_send_message tool do? +

sendook_send_message. It is categorised as a Write tool in the Sendook MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sendook_send_message? +

Register the Sendook MCP server in PolicyLayer and add a rule for sendook_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 Sendook. Nothing to install.

What risk level is sendook_send_message? +

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

Can I rate-limit sendook_send_message? +

Yes. Add a rate_limit block to the sendook_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 sendook_send_message completely? +

Set action: deny in the PolicyLayer policy for sendook_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 sendook_send_message? +

sendook_send_message is provided by the Sendook MCP server (streamlinedstartup/sendook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.