postgres_list_tables
AI agents call postgres_list_tables to retrieve information from MCP Postgres Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries database schema information (table listings) with no side effects. It does not modify, delete, or execute arbitrary code—it simply enumerates existing database tables. The empty description lowers confidence slightly, but the function name is unambiguous.
From the tool's definition Tool name is 'postgres_list_tables' which retrieves table metadata from a PostgreSQL database. Description is empty, but the name indicates a read-only operation that lists database objects without modification.
Attacks that exploit this kind of access
postgres_list_tables. It is categorised as a Read tool in the MCP Postgres Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Postgres Server 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 Postgres Server. 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 Postgres Server MCP server (madebynando/mcp-postgres-server). 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 →