Generate the current 6-digit TOTP code. Works on any credential that has a TOTP secret. Response also includes backupCodesRemaining (count of stored single-use recovery codes); call vault_totp_use_backup when the live TOTP is unavailable.
AI agents call vault_totp to retrieve information from Mailgent MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads/generates a TOTP code from a stored secret — it doesn't modify data, so it's a Read operation. However, severity is high because TOTP codes are authentication credentials; an AI agent misusing this tool could expose live one-time passwords that enable account takeovers or bypass MFA protections on external services.
From the tool's definition Generate the current 6-digit TOTP code... Response also includes backupCodesRemaining
Attacks that exploit this kind of access
Generate the current 6-digit TOTP code. Works on any credential that has a TOTP secret. Response also includes backupCodesRemaining (count of stored single-use recovery codes); call vault_totp_use_backup when the live TOTP is unavailable. It is categorised as a Read tool in the Mailgent MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mailgent MCP Server MCP server in PolicyLayer and add a rule for vault_totp: 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 Mailgent MCP Server. Nothing to install.
vault_totp 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 vault_totp 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 vault_totp. 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.
vault_totp is provided by the Mailgent MCP Server MCP server (loomal-ai/loomal-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 →