mailbox_action

Unified Inbox Agent workflow over Gmail or IMAP mailboxes: sync, score threads, summarize, draft replies, extract commitments, review bulk cleanup/follow-ups, and apply approved actions.

SERVERCoWork OS SOURCECoWork-OS/CoWork-OS

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/cowork-os/mailbox-action.md

WHAT IT DOES

What mailbox_action does on CoWork OS

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

RISK

Why mailbox_action is rated Medium

Although this tool includes read-like operations (sync, score, summarize, extract), it explicitly performs reversible modifications to mailbox state through drafting replies and applying approved actions. It does not irreversibly delete data (which would be Destructive) nor execute arbitrary code (Execute).

From the tool's definition Tool performs multiple write operations including 'draft replies' and 'apply approved actions' on mailboxes.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs mailbox_action safely

PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mailbox_action, this is the rule to start with:

mailbox_action Rate-limited

mailbox_action 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": {
    "mailbox_action": {
      "limits": [
        {
          "counter": "mailbox_action_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every mailbox_action call is checked against it from then on.

FAQ

Questions about mailbox_action

What does the mailbox_action tool do? +

Unified Inbox Agent workflow over Gmail or IMAP mailboxes: sync, score threads, summarize, draft replies, extract commitments, review bulk cleanup/follow-ups, and apply approved actions. It is categorised as a Write tool in the CoWork OS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mailbox_action? +

Register the CoWork OS MCP server in PolicyLayer and add a rule for mailbox_action: 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 CoWork OS. Nothing to install.

What risk level is mailbox_action? +

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

Can I rate-limit mailbox_action? +

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

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

mailbox_action is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on CoWork OS, and thousands of servers like it.

This server

All 342 CoWork OS tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →