AI agents call describe-table to retrieve information from BigQuery 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 and returns table schema information with no side effects. It is a straightforward metadata inspection operation that does not modify data, execute code, delete resources, or initiate financial transactions. The low severity reflects minimal blast radius—even if an AI misuses this tool, it can only view table structure information, which poses minimal risk.
From the tool's definition Tool name 'describe-table' and description 'Describes the schema of a specific table' indicate a read-only query that retrieves metadata about table structure without modification or execution of arbitrary operations.
Documented attack patterns abuse exactly the kind of access describe-table gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and BigQuery MCP server, and nothing reaches the server without passing your rules. This is the rule we recommend for describe-table:
{
"version": "1",
"default": "deny",
"tools": {
"describe-table": {}
}
}describe-table is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Describes the schema of a specific table. It is categorised as a Read tool in the BigQuery MCP server MCP Server, which means it retrieves data without modifying state.
Register the BigQuery 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 BigQuery 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 BigQuery MCP server MCP server (lucashild/mcp-server-bigquery). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from BigQuery MCP server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 BigQuery MCP server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.