AI agents call describe_table to retrieve information from Mcp Query without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs metadata inspection only, retrieving information about table schema. It has no side effects, does not execute code, and does not modify or delete data. The low severity reflects minimal blast radius: an agent misusing this tool could only learn about table structures, not access sensitive data or cause harm. The high confidence stems from the unambiguous read-only nature of schema introspection.
From the tool's definition Tool 'describe_table' is described as showing 'the structure of a database table (columns, types, keys)' — a pure inspection operation that retrieves metadata without modifying data or executing arbitrary operations.
Attacks that exploit this kind of access
Show the structure of a database table (columns, types, keys). It is categorised as a Read tool in the Mcp Query MCP Server, which means it retrieves data without modifying state.
Register the Mcp Query 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 Mcp Query. 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 Mcp Query MCP server (ottimis/mcp-query). 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 →