gmail_send · Access MCP: Risk & Policy

WHAT IT DOES

What gmail_send does on Access

AI agents invoke gmail_send to trigger actions in Access. 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 gmail_send needs a policy

Sending an email is an external operation with immediate real-world side effects — the message is delivered to recipients the moment the tool succeeds. This is not merely writing data into a store; it triggers an irreversible external communication.

From the tool's definition "Send an email from a configured Google account" and "Side effect: delivers the email immediately upon success"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gmail_send Rate-limited

gmail_send 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": {
    "gmail_send": {
      "limits": [
        {
          "counter": "gmail_send_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 Access, so you can run agents against it safely.

FAQ

Questions about gmail_send

What does the gmail_send tool do? +

Send an email from a configured Google account. Supports new messages and replies. Side effect: delivers the email immediately upon success. Returns the sent message ID. It is categorised as a Execute tool in the Access MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on gmail_send? +

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

What risk level is gmail_send? +

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

Can I rate-limit gmail_send? +

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

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

gmail_send is provided by the Access MCP server (scottpedia0/access). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.