Manage Vault secrets: read, write, delete, list. Supports KV v2 secrets engine.
AI agents call vault_secret to permanently remove resources in RedisNexus — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the tool includes read and write operations (which would normally classify as Read and Write respectively), the presence of 'delete' functionality elevates this to Destructive, as deletion of secrets cannot be undone and would have severe operational consequences.
From the tool's definition The tool description explicitly states it supports 'read, write, delete, list' operations on Vault secrets. The 'delete' capability means it can irreversibly remove sensitive secrets from the vault.
Attacks that exploit this kind of access
Manage Vault secrets: read, write, delete, list. Supports KV v2 secrets engine. It is categorised as a Destructive tool in the RedisNexus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RedisNexus MCP server in PolicyLayer and add a rule for vault_secret: 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.
vault_secret is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the vault_secret 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 vault_secret. 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.
vault_secret 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 →