Get table structure
AI agents call describe_table to retrieve information from PostgreSQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves schema metadata about a table's structure (column names, types, constraints) without modifying any data. It is a pure read operation with no side effects, consistent with the server's read-only design. The low severity reflects minimal blast radius—an AI agent could only expose schema information, not access or modify actual data values.
From the tool's definition Tool name is 'describe_table' with description 'Get table structure'. The server description explicitly states 'secure, read-only access' and lists this alongside 'querying data' and 'listing tables' as read operations.
Attacks that exploit this kind of access
Get table structure. It is categorised as a Read tool in the PostgreSQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PostgreSQL MCP Server 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 PostgreSQL MCP Server. 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 PostgreSQL MCP Server MCP server (psreekrishnan/postgresql-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 →