Get cost breakdown by user
AI agents call get_cost_by_user to retrieve information from BigQuery FinOps MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries cost data organized by user attribution. It is a read-only operation that provides visibility into spending metrics with no side effects, reversible modifications, code execution, data destruction, or financial movement. The low severity reflects that misuse would only expose financial information rather than alter systems or trigger transactions.
From the tool's definition Tool name 'get_cost_by_user' and description 'Get cost breakdown by user' indicate data retrieval without modification. No language suggesting creation, modification, deletion, execution, or financial transactions.
Attacks that exploit this kind of access
Get cost breakdown by user. It is categorised as a Read tool in the BigQuery FinOps MCP Server MCP Server, which means it retrieves data without modifying state.
Register the BigQuery FinOps MCP Server MCP server in PolicyLayer and add a rule for get_cost_by_user: 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 FinOps MCP Server. Nothing to install.
get_cost_by_user 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_cost_by_user 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_cost_by_user. 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_cost_by_user is provided by the BigQuery FinOps MCP Server MCP server (urfanazad/bq_azure_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 →