Dry-run a SQL query to see how many bytes it would scan without actually executing it. Use this before running expensive queries to check cost.
AI agents call query_cost_estimate 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 metadata about query execution cost without reading, writing, deleting, or executing actual data operations. It is a pure information retrieval mechanism (Read category). Severity is low because misuse cannot corrupt, delete, or access sensitive data—it only returns cost estimates. The high confidence reflects the clear, explicit description of its dry-run nature.
From the tool's definition Tool description states it performs a 'dry-run' of a SQL query to estimate bytes scanned 'without actually executing it.' The explicit purpose is cost estimation, which produces no side effects on data.
Documented attack patterns abuse exactly the kind of access query_cost_estimate 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 query_cost_estimate:
{
"version": "1",
"default": "deny",
"tools": {
"query_cost_estimate": {}
}
}query_cost_estimate 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.
Dry-run a SQL query to see how many bytes it would scan without actually executing it. Use this before running expensive queries to check cost. 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 query_cost_estimate: 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.
query_cost_estimate 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 query_cost_estimate 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 query_cost_estimate. 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.
query_cost_estimate 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.