Retrieve a decrypted credential from the vault. For TOTP credentials, use vault_totp instead to get the code.
AI agents call vault_get 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.
Although this tool retrieves sensitive credentials (high severity due to exposure of secrets), the action itself is read-only with no side effects. Retrieving credentials does not modify, delete, or execute operations.
From the tool's definition Tool name 'vault_get' and description 'Retrieve a decrypted credential from the vault' indicate data retrieval without modification. The action is fundamentally a read operation that returns stored secrets.
Attacks that exploit this kind of access
Retrieve a decrypted credential from the vault. For TOTP credentials, use vault_totp instead to get the code. 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_get: 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_get 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_get 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_get. 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_get 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 →