Get detailed table information with schema and column fill rate analysis
AI agents call get_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 performs introspection on table structure and statistics (schema, column fill rates). It is a pure retrieval operation with no side effects—it queries metadata only. The server explicitly markets itself as 'safe read-only', and this tool fits squarely into that paradigm. Misuse by an AI agent would only expose data structure information, not modify or destroy anything.
From the tool's definition Tool description: 'Get detailed table information with schema and column fill rate analysis'. Server description: 'run safe read-only queries'. The tool retrieves table metadata and schema information with no modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access get_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 get_table:
{
"version": "1",
"default": "deny",
"tools": {
"get_table": {}
}
}get_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.
Get detailed table information with schema and column fill rate analysis. 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 get_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.
get_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 get_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 get_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.
get_table is provided by the BigQuery MCP Server MCP server (pvoo/bigquery-mcp). 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.
5 BigQuery MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.