Search for credential items in vaults accessible to this token. Returns item handles with non-sensitive field values (e.g. username). Sensitive values (e.g. password) are only available via the local blind-fill MCP tool.
AI agents call vault_search to retrieve information from Shellgate 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 query operation that retrieves metadata about credentials without exposing secrets. However, it reveals sensitive information structure (usernames, account identifiers, vault organization) that could inform social engineering or targeted attacks.
From the tool's definition Tool 'searches for credential items in vaults' and 'returns item handles with non-sensitive field values'. Sensitive values explicitly withheld and 'only available via the local blind-fill MCP tool'.
Documented attack patterns abuse exactly the kind of access vault_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Shellgate, and nothing reaches the server without passing your rules. This is the rule we recommend for vault_search:
{
"version": "1",
"default": "deny",
"tools": {
"vault_search": {}
}
}vault_search 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 for credential items in vaults accessible to this token. Returns item handles with non-sensitive field values (e.g. username). Sensitive values (e.g. password) are only available via the local blind-fill MCP tool. It is categorised as a Read tool in the Shellgate MCP Server, which means it retrieves data without modifying state.
Register the Shellgate MCP server in PolicyLayer and add a rule for vault_search: 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 Shellgate. Nothing to install.
vault_search 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_search 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_search. 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_search is provided by the Shellgate MCP server (matthiastjong/shellgate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Shellgate, 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.
31 Shellgate tools catalogued and risk-classified — across an index of 43,000+ MCP servers.