// SCAN REPORT

Op

10 tools. 3 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

3 can modify or destroy data

7 read-only

10 tools total

Community server · catalogue entry verified 03/07/2026

How to control Op ↓

TOOL MAP

What Op exposes to your agents

Read (7) Write / Execute (2) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Op tools

Destructive · Critical op_delete_item Deletion of vault items in a password manager is a destructive action that cannot be undone. Write · High op_create_item op_create_item creates new password vault entries. Write · High op_edit_item This tool modifies 1Password vault items (passwords, secrets, credentials) but the changes are reversible (can be edited again or undone), placing it in Write rather than Destructive.

3 of Op's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Op

PolicyLayer is an MCP gateway — it sits between your AI agents and Op, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "op_delete_item": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "op_create_item": {
    "limits": [
      {
        "counter": "op_create_item_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "op_get_item": {
    "limits": [
      {
        "counter": "op_get_item_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Op — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON OP →

Instant setup, no code required.

FULL CATALOGUE

All 10 Op tools

DESTRUCTIVE 1 tools

Destructive op_delete_item op_delete_item

WRITE 2 tools

Write op_create_item op_create_item Write op_edit_item op_edit_item

READ 7 tools

Read op_get_item op_get_item Read op_list_items List items in a 1Password vault. Read op_list_vaults List all 1Password vaults the authenticated account can access. Read op_ping Liveness check for the MCP server. Does not invoke the op CLI. Read op_read_secret op_read_secret Read op_version Return the version of the op CLI binary. No auth required. Read op_whoami Return the currently authenticated 1Password account.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Op

Can an AI agent delete data through the Op MCP server? +

Yes. The Op server exposes 1 destructive tools including op_delete_item. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Op? +

The Op server has 2 write tools including op_create_item, op_edit_item. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Op.

How many tools does the Op MCP server expose? +

10 tools across 4 categories: Destructive, Execute, Read, Write. 7 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Op? +

Register the Op MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Op tool call.

Deterministic rules across all 10 Op tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OP →

Instant setup, no code required.

10 Op tools catalogued and risk-classified — across an index of 43,000+ MCP servers.