AI agents call describe_table to retrieve information from MCP-Maker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries structural metadata about a table (schema, column names, data types). It has no capability to modify, delete, execute code, or affect data. It is a read-only introspection operation, making it the lowest-risk category. The low severity reflects minimal blast radius—exposing table schemas is typically acceptable and often necessary for legitimate data access workflows.
From the tool's definition Tool name 'describe_table' and description 'Get the schema (columns and types) for a specific table' indicates retrieval of metadata with no side effects.
Attacks that exploit this kind of access
Get the schema (columns and types) for a specific table. It is categorised as a Read tool in the MCP-Maker MCP Server, which means it retrieves data without modifying state.
Register the MCP-Maker 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-Maker. 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-Maker MCP server (mralihasan/mcp-maker). 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 →