Find credentials matching a search query. Returns matching handles with relevance scores. You will never see credential values.
AI agents call vault_find to retrieve information from Kova Mind MCP Server 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 operation that queries a credential vault to find matching handles. It returns metadata (handles and relevance scores) but not the actual credential values, making it a safe information retrieval tool with no side effects. The credential values remain protected in the vault.
From the tool's definition Tool performs a search query on stored credentials and "Returns matching handles with relevance scores". It explicitly states "You will never see credential values", confirming it retrieves metadata only without exposing secrets.
Attacks that exploit this kind of access
Find credentials matching a search query. Returns matching handles with relevance scores. You will never see credential values. It is categorised as a Read tool in the Kova Mind MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kova Mind MCP Server MCP server in PolicyLayer and add a rule for vault_find: 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_find 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 vault_find 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_find. 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_find 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 →