Run one script with 1Password CLI auth injected by the MCP process. In normal mode this runs a startup-configured allowlisted commandId. When --enable-unrestricted-script-runner=true is set, startup allowlists are ignored and this accepts a free-form command after one local browser approval per M...
AI agents invoke op_script_run to trigger actions in Mcp 1password. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool enables execution of scripts and commands (potentially arbitrary when unrestricted mode is enabled), with automatic credential injection from 1Password. While it includes allowlisting as a control, the explicit mention of 'free-form command' acceptance and dynamic script execution makes this an Execute-category risk.
From the tool's definition Tool description states 'Run one script with 1Password CLI auth injected' and explicitly supports 'free-form command' execution when unrestricted mode is enabled.
Attacks that exploit this kind of access
Run one script with 1Password CLI auth injected by the MCP process. In normal mode this runs a startup-configured allowlisted commandId. When --enable-unrestricted-script-runner=true is set, startup allowlists are ignored and this accepts a free-form command after one local browser approval per MCP process. ${SCRIPT_RUNNER_SECRET_HINT} Use this instead of password_read reveal or secret_reveal when the secret only needs to be passed to a script. If returnOutput=true is requested for secret-injected or sensitive output without plaintext acknowledgement, execution is skipped and the required acknowledgement is returned. It is categorised as a Execute tool in the Mcp 1password MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp 1password MCP server in PolicyLayer and add a rule for op_script_run: 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.
op_script_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the op_script_run 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 op_script_run. 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.
op_script_run 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 →