Get vault accessor permissions. The JS SDK beta exposes this through vault accessors.
AI agents call vault_permissions_get to retrieve information from Mcp 1password without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves permission metadata about vault accessors, which is a read-only operation. It poses medium severity because exposing vault permission structures could help an attacker map security boundaries and identify high-privilege targets, even though no data is modified.
From the tool's definition Tool name 'vault_permissions_get' and description 'Get vault accessor permissions' indicate a data retrieval operation with no modification or deletion. However, the description is sparse and references 'vault accessors' without clarifying scope.
Attacks that exploit this kind of access
Get vault accessor permissions. The JS SDK beta exposes this through vault accessors. It is categorised as a Read tool in the Mcp 1password MCP Server, which means it retrieves data without modifying state.
Register the Mcp 1password MCP server in PolicyLayer and add a rule for vault_permissions_get: 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 Mcp 1password. Nothing to install.
vault_permissions_get 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_permissions_get 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_permissions_get. 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_permissions_get is provided by the Mcp 1password MCP server (kefapps/onepassword-mcp-codex). 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 →