Fetches GCP cost breakdown by service and project from BigQuery billing export for a given time period. Use this to answer questions about overall GCP spend, top spending services, or cost by project.
AI agents call get_gcp_cost_summary to retrieve information from Cloud FinOps Analyst MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only query of existing GCP cost data from BigQuery. It retrieves and summarizes financial information but does not create, modify, delete, or move money. While it accesses financial data (which could inform decision-making), it does not itself commit financial transactions or obligations.
From the tool's definition Tool description states it 'Fetches GCP cost breakdown by service and project from BigQuery billing export for a given time period' — this is a retrieval operation that queries billing data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Fetches GCP cost breakdown by service and project from BigQuery billing export for a given time period. Use this to answer questions about overall GCP spend, top spending services, or cost by project. It is categorised as a Read tool in the Cloud FinOps Analyst MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cloud FinOps Analyst MCP Server MCP server in PolicyLayer and add a rule for get_gcp_cost_summary: 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 Cloud FinOps Analyst MCP Server. Nothing to install.
get_gcp_cost_summary 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 get_gcp_cost_summary 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 get_gcp_cost_summary. 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.
get_gcp_cost_summary is provided by the Cloud FinOps Analyst MCP Server MCP server (mihirkadam19/finops-mcp-server). 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 →