Execute read-only BigQuery SQL queries with safety validation. Use LIMIT in your query to control result size (recommended: start with LIMIT 20). For semantic search, consider using the vector_search tool or write custom VECTOR_SEARCH queries.
AI agents invoke run_query to trigger actions in BigQuery MCP Server. 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 tool executes SQL queries, placing it in the Execute category. Although described as read-only with safety validation, arbitrary SQL execution carries high risk: safety validation may be bypassable, queries could scan massive datasets incurring cost, expose sensitive data, or (if validation fails) permit destructive operations.
From the tool's definition "Execute read-only BigQuery SQL queries with safety validation" — the tool runs SQL queries against BigQuery. Despite claims of read-only enforcement via 'safety validation', it executes arbitrary SQL provided as arguments.
Documented attack patterns abuse exactly the kind of access run_query 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 run_query:
{
"version": "1",
"default": "deny",
"tools": {
"run_query": {
"limits": [
{
"counter": "run_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute read-only BigQuery SQL queries with safety validation. Use LIMIT in your query to control result size (recommended: start with LIMIT 20). For semantic search, consider using the vector_search tool or write custom VECTOR_SEARCH queries. It is categorised as a Execute tool in the BigQuery MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the BigQuery MCP Server MCP server in PolicyLayer and add a rule for run_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 BigQuery MCP Server. Nothing to install.
run_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 run_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 run_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.
run_query 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.