Unlock the secrets vault with your passphrase. Required before storing or using credentials.
AI agents invoke vault_unlock to trigger actions in Kova Mind MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes an authentication/authorization operation that changes the state of the vault from locked to unlocked, enabling subsequent access to stored credentials. It is not a simple read (it changes vault state) nor destructive, but it triggers an external security operation — unlocking a credential store — whose misuse could expose all stored secrets.
From the tool's definition "Unlock the secrets vault with your passphrase. Required before storing or using credentials."
Attacks that exploit this kind of access
Unlock the secrets vault with your passphrase. Required before storing or using credentials. It is categorised as a Execute tool in the Kova Mind MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kova Mind MCP Server MCP server in PolicyLayer and add a rule for vault_unlock: 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 Kova Mind MCP Server. Nothing to install.
vault_unlock is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the vault_unlock 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_unlock. 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_unlock is provided by the Kova Mind MCP Server MCP server (kovamind/mcp-server). 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 →