Inspect Terraform state: list resources, show details, detect drift potential.
AI agents call tf_state 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 retrieves and analyzes infrastructure state data (resources, details, drift detection) with no side effects. However, severity is elevated to 'high' because Terraform state typically contains sensitive information (database passwords, API keys, private IPs, credential references), and unauthorized read access could expose production infrastructure secrets and topology to an AI agent, enabling lateral…
From the tool's definition Tool performs inspection operations: "list resources, show details, detect drift potential" — all read-only actions that query Terraform state without modifying or deleting it.
Attacks that exploit this kind of access
Inspect Terraform state: list resources, show details, detect drift potential. 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 tf_state: 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.
tf_state 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 tf_state 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 tf_state. 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.
tf_state 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 →