GCP IAM — list service accounts, roles, get project IAM policy.
AI agents call gcp_iam to retrieve information from RedisNexus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs read-only operations (list, get) on GCP IAM data. However, severity is medium rather than low because IAM policy information is sensitive and could expose security configuration details that an adversary might leverage for privilege escalation planning, even though the tool itself cannot execute such escalation.
From the tool's definition Tool description states 'list service accounts, roles, get project IAM policy' — all query/retrieval operations with no modification or execution capabilities.
Attacks that exploit this kind of access
GCP IAM — list service accounts, roles, get project IAM policy. It is categorised as a Read tool in the RedisNexus MCP Server, which means it retrieves data without modifying state.
Register the RedisNexus MCP server in PolicyLayer and add a rule for gcp_iam: 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 RedisNexus. Nothing to install.
gcp_iam 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 gcp_iam 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 gcp_iam. 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.
gcp_iam is provided by the RedisNexus MCP server (rajkumar-madhu/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 →