AI agents call postgres-list-tables to retrieve information from Mcp Gmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the low confidence due to missing documentation, the naming convention strongly suggests this is a database metadata query. The 'list' operation retrieves information about tables without side effects. The empty description and the tool appearing on a Gmail server (which seems incongruent) lowers confidence, but the standard semantics of 'list-tables' indicate a Read operation.
From the tool's definition Tool name contains 'list' which typically indicates a query/enumeration operation. The empty description prevents full assessment, but 'list-tables' is a standard database inspection command with no modification or execution capability.
Attacks that exploit this kind of access
postgres-list-tables. It is categorised as a Read tool in the Mcp Gmail MCP Server, which means it retrieves data without modifying state.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for postgres-list-tables: 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 Gmail. Nothing to install.
postgres-list-tables 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 postgres-list-tables 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 postgres-list-tables. 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.
postgres-list-tables is provided by the Mcp Gmail MCP server (@monsoft/mcp-gmail). 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 →