Get one group by ID. This is the only group read endpoint exposed by the official JS SDK beta today.
AI agents call group_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 group information from 1Password without modifying, deleting, or executing any operations. It is a simple data retrieval endpoint that poses minimal risk as it only queries existing data. The low severity reflects the read-only nature and limited blast radius of misuse.
From the tool's definition Tool name 'group_get' and description 'Get one group by ID' indicate a retrieval operation. The phrase 'read endpoint' in the description explicitly confirms this is a read-only operation with no side effects.
Attacks that exploit this kind of access
Get one group by ID. This is the only group read endpoint exposed by the official JS SDK beta today. 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 group_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.
group_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 group_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 group_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.
group_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 →