bigquery_last_n_query
AI agents invoke bigquery_last_n_query to trigger actions in GCP MCP Log Diagnostics. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The name implies running queries against BigQuery, which is an Execute-level action (running SQL that could be arbitrary). However, the empty description significantly lowers confidence. Given the server context (GCP log diagnostics), it likely retrieves recent query results, but 'query' execution against BigQuery warrants at least Execute classification.
From the tool's definition Tool name 'bigquery_last_n_query' suggests execution of BigQuery queries; description is empty and uninformative.
Attacks that exploit this kind of access
bigquery_last_n_query. It is categorised as a Execute tool in the GCP MCP Log Diagnostics MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GCP MCP Log Diagnostics MCP server in PolicyLayer and add a rule for bigquery_last_n_query: 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 GCP MCP Log Diagnostics. Nothing to install.
bigquery_last_n_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the bigquery_last_n_query 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 bigquery_last_n_query. 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.
bigquery_last_n_query is provided by the GCP MCP Log Diagnostics MCP server (kanhaiworld/gcp_mcp). 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 →