AI agents call describe_table to retrieve information from Pg Pool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only introspection operation that queries system catalogs to return schema definitions. It has no side effects, creates no modifications, and poses minimal risk. It falls squarely under the 'Read' category as a data retrieval function with no capability to alter state.
From the tool's definition The tool 'describe_table' retrieves table schema metadata (columns, types, nullability, defaults, primary keys, foreign keys) without modifying data or executing arbitrary operations.
Attacks that exploit this kind of access
Get the schema of a table including columns, types, nullability, defaults, primary keys, and foreign keys. It is categorised as a Read tool in the Pg Pool MCP Server, which means it retrieves data without modifying state.
Register the Pg Pool 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 Pg Pool. 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 Pg Pool MCP server (sam-david/pg-pool-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 →