gcp-spanner-query-natural-language
AI agents invoke gcp-spanner-query-natural-language to trigger actions in Google Cloud 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 likely translates natural language into Spanner SQL queries and executes them. Since it accepts natural language input that gets converted to arbitrary SQL, it could execute queries ranging from read-only SELECTs to potentially destructive DML (DELETE, UPDATE, DROP). The most severe applicable category given the potential for arbitrary query execution is Execute.
From the tool's definition Tool name contains 'query' and 'natural-language', server description mentions 'interact with Spanner databases' through 'natural language interaction'
Documented attack patterns abuse exactly the kind of access gcp-spanner-query-natural-language gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Cloud MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for gcp-spanner-query-natural-language:
{
"version": "1",
"default": "deny",
"tools": {
"gcp-spanner-query-natural-language": {
"limits": [
{
"counter": "gcp-spanner-query-natural-language_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} gcp-spanner-query-natural-language 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.
gcp-spanner-query-natural-language. It is categorised as a Execute tool in the Google Cloud MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Google Cloud MCP Server MCP server in PolicyLayer and add a rule for gcp-spanner-query-natural-language: 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 Google Cloud MCP Server. Nothing to install.
gcp-spanner-query-natural-language 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 gcp-spanner-query-natural-language 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 gcp-spanner-query-natural-language. 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.
gcp-spanner-query-natural-language is provided by the Google Cloud MCP Server MCP server (krzko/google-cloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google Cloud 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.
40 Google Cloud MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.