Search secret names by regex pattern (case insensitive). Filtered by allowlist.
AI agents call search_secrets to retrieve information from Claude Secrets without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data (secret names) without side effects. It performs a search operation that does not create, modify, delete, or execute anything—only filters and returns matching secret names from the allowlist. This is a classic Read operation with minimal blast radius if misused by an AI agent (worst case: discovering what secrets exist, which is already constrained by the allowlist).
From the tool's definition Tool performs 'Search secret names by regex pattern' with no modification, deletion, or execution capabilities. Returns filtered results matching the allowlist criteria.
Documented attack patterns abuse exactly the kind of access search_secrets gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Secrets, and nothing reaches the server without passing your rules. This is the rule we recommend for search_secrets:
{
"version": "1",
"default": "deny",
"tools": {
"search_secrets": {}
}
}search_secrets is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search secret names by regex pattern (case insensitive). Filtered by allowlist. It is categorised as a Read tool in the Claude Secrets MCP Server, which means it retrieves data without modifying state.
Register the Claude Secrets MCP server in PolicyLayer and add a rule for search_secrets: 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 Claude Secrets. Nothing to install.
search_secrets 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 search_secrets 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 search_secrets. 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.
search_secrets is provided by the Claude Secrets MCP server (vaultry/claude-secrets). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Secrets, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Claude Secrets tools catalogued and risk-classified — across an index of 43,000+ MCP servers.