mailtarget_call_endpoint · Mailtarget MCP: Risk & Policy

WHAT IT DOES

What mailtarget_call_endpoint does on Mailtarget

AI agents invoke mailtarget_call_endpoint to trigger actions in Mailtarget. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why mailtarget_call_endpoint needs a policy

This tool executes arbitrary API calls against a live account, including potentially destructive or mutating operations (POST/PUT/DELETE). Since it can span multiple categories depending on the operationId provided, the most severe applicable category is Execute (and potentially Destructive), given it can perform deletions and mutations on the live account.

From the tool's definition "Execute a Mailtarget API call" and "Mutating calls (POST/PUT/DELETE) act on the live account, use with care"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mailtarget_call_endpoint Rate-limited

mailtarget_call_endpoint stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mailtarget_call_endpoint": {
      "limits": [
        {
          "counter": "mailtarget_call_endpoint_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mailtarget, so you can run agents against it safely.

FAQ

Questions about mailtarget_call_endpoint

What does the mailtarget_call_endpoint tool do? +

Execute a Mailtarget API call against api.mailtarget.co (Bearer auth from MAILTARGET_API_KEY). Provide operationId plus pathParams/query/body as needed. Mutating calls (POST/PUT/DELETE) act on the live account, use with care. It is categorised as a Execute tool in the Mailtarget MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mailtarget_call_endpoint? +

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

What risk level is mailtarget_call_endpoint? +

mailtarget_call_endpoint is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit mailtarget_call_endpoint? +

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

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

mailtarget_call_endpoint is provided by the Mailtarget MCP server (yopie-org/mailtarget). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.