Create a new email inbox
AI agents use create_inbox to create or update resources in AgentMail MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AgentMail MCP Server environment.
The tool creates a new resource (email inbox) with side effects, but the creation is reversible (the inbox can be deleted). It does not execute arbitrary code, destroy data, move money, or perform read-only operations. This is a straightforward Write action.
From the tool's definition Tool description states 'Create a new email inbox' — a create operation that establishes new persistent state in the email system.
Attacks that exploit this kind of access
Create a new email inbox. It is categorised as a Write tool in the AgentMail MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AgentMail MCP Server MCP server in PolicyLayer and add a rule for create_inbox: 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 AgentMail MCP Server. Nothing to install.
create_inbox 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_inbox 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_inbox. 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_inbox is provided by the AgentMail MCP Server MCP server (kamath/agentmail-mcp). 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 →