Forecast organic traffic using BigQuery ML ARIMA_PLUS. Trains a time-series model on your historical click data and projects future clicks with confidence intervals. Requires sufficient historical data (ideally 6+ months). This is only possible with BigQuery ML.
AI agents invoke gsc_forecast 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.
This tool trains a BigQuery ML model (ARIMA_PLUS) on historical data and executes forecasting computations. It goes beyond a simple read/query — it creates/trains an ML model and runs predictions, which constitutes executing an operation with computational side effects in BigQuery ML.
From the tool's definition Trains a time-series model on your historical click data and projects future clicks with confidence intervals. Requires sufficient historical data. This is only possible with BigQuery ML.
Documented attack patterns abuse exactly the kind of access gsc_forecast 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 gsc_forecast:
{
"version": "1",
"default": "deny",
"tools": {
"gsc_forecast": {
"limits": [
{
"counter": "gsc_forecast_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}gsc_forecast 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.
Forecast organic traffic using BigQuery ML ARIMA_PLUS. Trains a time-series model on your historical click data and projects future clicks with confidence intervals. Requires sufficient historical data (ideally 6+ months). This is only possible with BigQuery ML. 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 gsc_forecast: 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.
gsc_forecast 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 gsc_forecast 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 gsc_forecast. 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.
gsc_forecast 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.