Tests IAM permissions for a bucket.
AI agents call check_iam_permissions to retrieve information from Observability without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only check of IAM permissions on a GCP bucket. It queries existing permissions without creating, modifying, deleting, or executing any operations. The verb 'check' and 'test' confirm it is observational/diagnostic in nature.
From the tool's definition Tool name 'check_iam_permissions' and description 'Tests IAM permissions for a bucket' indicate a query operation that retrieves permission information without modifying state.
Attacks that exploit this kind of access
Tests IAM permissions for a bucket. It is categorised as a Read tool in the Observability MCP Server, which means it retrieves data without modifying state.
Register the Observability MCP server in PolicyLayer and add a rule for check_iam_permissions: 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 Observability. Nothing to install.
check_iam_permissions 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 check_iam_permissions 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 check_iam_permissions. 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.
check_iam_permissions is provided by the Observability MCP server (@google-cloud/observability-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 →