password_update · Mcp 1password MCP: Risk & Policy

WHAT IT DOES

What password_update does on Mcp 1password

AI agents use password_update to create or update resources in Mcp 1password — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp 1password environment.

WHY IT NEEDS A POLICY

Why password_update needs a policy

This tool modifies existing password data within 1Password items. While the operation itself is reversible (passwords can be changed again), the impact is high because: (1) incorrect password updates could lock users out of their actual accounts, (2) password changes may break dependent systems or automation, (3) updating passwords on behalf of users represents a significant security-sensitive modification.

From the tool's definition Tool description states 'Update or insert one concealed password field on an existing item', which is a modification operation. Returns 'redacted item metadata only', confirming data is being changed reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

password_update Rate-limited

password_update stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "password_update": {
      "limits": [
        {
          "counter": "password_update_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp 1password, so you can run agents against it safely.

FAQ

Questions about password_update

What does the password_update tool do? +

Update or insert one concealed password field on an existing item. Returns redacted item metadata only. It is categorised as a Write tool in the Mcp 1password MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on password_update? +

Register the Mcp 1password MCP server in PolicyLayer and add a rule for password_update: 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.

What risk level is password_update? +

password_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit password_update? +

Yes. Add a rate_limit block to the password_update 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.

How do I block password_update completely? +

Set action: deny in the PolicyLayer policy for password_update. 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.

What MCP server provides password_update? +

password_update 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.