audit_csp_tenants
AI agents call audit_csp_tenants to retrieve information from Azure FinOps Elite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Auditing is fundamentally a Read operation—it retrieves and reviews tenant data to assess compliance and security posture without modifying it. The medium severity reflects that an AI agent given this tool could potentially over-fetch sensitive multi-tenant cost/compliance data and leak it, but cannot directly cause financial loss or destructive changes.
From the tool's definition Tool name 'audit_csp_tenants' indicates inspection/review of Cloud Service Provider tenants with no mutation language (no 'create', 'delete', 'update', 'modify'); sibling tools like 'detect_anomalies', 'validate_budget', and 'get_governance_recommendations'…
Attacks that exploit this kind of access
audit_csp_tenants. It is categorised as a Read tool in the Azure FinOps Elite MCP Server, which means it retrieves data without modifying state.
Register the Azure FinOps Elite MCP server in PolicyLayer and add a rule for audit_csp_tenants: 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 Azure FinOps Elite. Nothing to install.
audit_csp_tenants 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 audit_csp_tenants 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 audit_csp_tenants. 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.
audit_csp_tenants is provided by the Azure FinOps Elite MCP server (mazhar480/azure-finops-optimizer-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 →