Preview sample rows from a table without writing SQL. Useful for quickly understanding what data looks like. Limited to 1GB bytes billed.
AI agents call sample_rows 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.
sample_rows retrieves and displays sample data from a BigQuery table for inspection purposes. This is a non-destructive data retrieval operation with no side effects. The 1GB billing limit confirms it is a bounded read query. No write, execute, destructive, or financial operations are possible with this tool.
From the tool's definition Tool description states 'Preview sample rows from a table without writing SQL' and 'Limited to 1GB bytes billed.' The operation is read-only with no mention of modifications, deletions, or state-changing side effects.
Documented attack patterns abuse exactly the kind of access sample_rows 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 sample_rows:
{
"version": "1",
"default": "deny",
"tools": {
"sample_rows": {}
}
}sample_rows 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.
Preview sample rows from a table without writing SQL. Useful for quickly understanding what data looks like. Limited to 1GB bytes billed. 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 sample_rows: 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.
sample_rows 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 sample_rows 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 sample_rows. 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.
sample_rows is provided by the BigQuery MCP Server MCP server (suganthan-mohanadasan/suganthans-bigquery-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 32 BigQuery MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
32 BigQuery MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.