Returns the schema (column names, types, and constraints) for a specified table.
AI agents call describe_table to retrieve information from Hospital MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
describe_table is purely informational—it queries database metadata to understand table structure. It cannot retrieve actual data rows, modify data, delete data, or trigger external operations. The blast radius of misuse is minimal: an attacker might learn database schema to inform further attacks, but the tool itself performs no harmful action. This is a classic Read category tool with low severity.
From the tool's definition Tool returns schema information (column names, types, and constraints) for a specified table. No data retrieval beyond structural metadata, no modifications, no deletion, no external operations.
Attacks that exploit this kind of access
Returns the schema (column names, types, and constraints) for a specified table. It is categorised as a Read tool in the Hospital MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hospital 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 Hospital 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 Hospital MCP Server MCP server (sheshugit/mcp_postgres). 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 →