AI agents call get-billing-info to retrieve information from GCP MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves billing data without modifying, deleting, or executing operations. However, severity is medium rather than low because billing information is sensitive financial data that could expose cost structures, payment methods, or account details if disclosed to unauthorized users, though the tool itself performs no financial transactions.
From the tool's definition Tool name 'get-billing-info' and description 'Get billing information for the current project' indicate data retrieval with no modification. The verb 'get' is typical of Read operations.
Attacks that exploit this kind of access
Get billing information for the current project. It is categorised as a Read tool in the GCP MCP MCP Server, which means it retrieves data without modifying state.
Register the GCP MCP server in PolicyLayer and add a rule for get-billing-info: 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 GCP MCP. Nothing to install.
get-billing-info 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-billing-info 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-billing-info. 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-billing-info is provided by the GCP MCP server (radiumgu/gcp-ops-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 →