Wait for a verification code to arrive in a mailbox. Polls until a code is found or timeout is reached.
AI agents call wait_for_code to retrieve information from agentsbase — Email for AI Agents without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/polls a mailbox waiting for a verification code to arrive — it does not send emails, create mailboxes, or modify any data. It is a read/query operation. Severity is medium because verification codes are sensitive authentication artifacts; misuse could allow an AI agent to intercept OTPs or 2FA codes intended for account access, enabling account takeover.
From the tool's definition Wait for a verification code to arrive in a mailbox. Polls until a code is found or timeout is reached.
Attacks that exploit this kind of access
Wait for a verification code to arrive in a mailbox. Polls until a code is found or timeout is reached. It is categorised as a Read tool in the agentsbase — Email for AI Agents MCP Server, which means it retrieves data without modifying state.
Register the agentsbase — Email for AI Agents MCP server in PolicyLayer and add a rule for wait_for_code: 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 agentsbase — Email for AI Agents. Nothing to install.
wait_for_code is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the wait_for_code 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 wait_for_code. 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.
wait_for_code is provided by the agentsbase — Email for AI Agents MCP server (agentsbase-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 →