Create a new mailbox/folder
AI agents use create_mailbox to create or update resources in MCP Mail Organizer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Mail Organizer environment.
This tool creates a new mailbox/folder, which is a reversible write operation that modifies email infrastructure by adding a new container. It does not retrieve data (Read), execute arbitrary code (Execute), irreversibly delete anything (Destructive), or move money (Financial).
From the tool's definition Tool name is 'create_mailbox' and description states 'Create a new mailbox/folder'. The action creates a new organizational structure within email infrastructure.
Attacks that exploit this kind of access
Create a new mailbox/folder. It is categorised as a Write tool in the MCP Mail Organizer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Mail Organizer MCP server in PolicyLayer and add a rule for create_mailbox: 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 MCP Mail Organizer. Nothing to install.
create_mailbox is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_mailbox 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.
Set action: deny in the PolicyLayer policy for create_mailbox. 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.
create_mailbox is provided by the MCP Mail Organizer MCP server (neomody77/mcp-mail-organizer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →