Describe the structure of a table including columns, types, and constraints.
AI agents call describe_table to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns structural information about a table (column definitions, types, constraints) but does not query data, modify any database state, or execute arbitrary operations. It is a standard schema inspection capability with no side effects. Low severity because schema information is typically non-sensitive or already accessible to authenticated database users.
From the tool's definition Tool name 'describe_table' and description 'Describe the structure of a table including columns, types, and constraints' indicate schema introspection without data retrieval or modification. This is a read-only metadata operation.
Documented attack patterns abuse exactly the kind of access describe_table gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Postgres, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_table:
{
"version": "1",
"default": "deny",
"tools": {
"describe_table": {}
}
} describe_table is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Describe the structure of a table including columns, types, and constraints. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for describe_table: 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 Postgres. Nothing to install.
describe_table 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 describe_table 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 describe_table. 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.
describe_table is provided by the Postgres MCP server (javimaligno/postgres_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Postgres, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Postgres tools catalogued and risk-classified — across an index of 43,000+ MCP servers.