AI agents call describe_table to retrieve information from Querywise without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The describe_table tool performs a read-only operation that retrieves table structure/metadata from a SQL database. This has no side effects, does not modify data, and aligns with the server's stated 'read-only by default' design. The low severity reflects minimal blast radius—an agent invoking this tool can only discover schema information, not execute queries, modify data, or delete resources.
From the tool's definition Tool name 'describe_table' and server context indicate metadata retrieval. Server description emphasizes 'Read-only by default' and describes a semantic layer for querying SQL databases. The tool retrieves table schema information without modifying data.
Attacks that exploit this kind of access
describe_table. It is categorised as a Read tool in the Querywise MCP Server, which means it retrieves data without modifying state.
Register the Querywise 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 Querywise. 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 Querywise MCP server (kosminus/querywise-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 →