Inspect RBAC: roles, cluster roles, bindings. Understand who has access to what.
AI agents call k8s_rbac 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.
This is a read-only tool for querying Kubernetes RBAC metadata. While the information it exposes (access control policies) is sensitive and could inform privilege escalation attacks if misused, the tool itself performs no writes, deletions, or execution.
From the tool's definition Tool name 'k8s_rbac' and description 'Inspect RBAC: roles, cluster roles, bindings. Understand who has access to what' — verbs are 'Inspect' and 'Understand', both read-only operations.
Attacks that exploit this kind of access
Inspect RBAC: roles, cluster roles, bindings. Understand who has access to what. 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 k8s_rbac: 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.
k8s_rbac 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 k8s_rbac 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 k8s_rbac. 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.
k8s_rbac 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 →