// SCAN REPORT

1pass

15 tools. 5 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 5 Oct 2026

5 can modify or destroy data

10 read-only

15 tools total

Community server · catalogue entry checked 05/10/2026 · full schemas captured for 9 of 15 tools

How to control 1pass ↓

TOOL MAP

What 1pass exposes to your agents

Read (10) Write / Execute (2) Destructive / Financial (3)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What 1pass costs in tokens

1,570 tokens of tool definitions, loaded on every request

0.8% of a 200k context window

161 heaviest tool: logi_add_redirect_uri

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous 1pass tools

Destructive · High logi_delete_login_log Use when the user wants to remove a specific login record from view (e.g. 'delete that suspicious entry'). Soft-delete only — recoverable fo Destructive · High logi_delete_passkey Use when the user explicitly asks to remove a specific passkey (e.g. lost device, old laptop). Destructive and irreversible — confirm with t Destructive · High logi_remove_redirect_uri Use when the user (RP owner) wants to deregister an old/unused OAuth callback URL — for example a historical onrender.com host that's been m Write · Medium logi_add_redirect_uri Use when the user (RP owner) wants to register a new OAuth callback URL — for example after deploying to a new domain (easybracket.org), add

5 of 1pass's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control 1pass

PolicyLayer is an MCP gateway — it sits between your AI agents and 1pass, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "logi_delete_login_log": {
    "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

{
  "logi_add_redirect_uri": {
    "limits": [
      {
        "counter": "logi_add_redirect_uri_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "logi_fetch_quickstart": {
    "limits": [
      {
        "counter": "logi_fetch_quickstart_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 1pass — 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 1PASS →

Instant setup, no code required.

FULL CATALOGUE

All 15 1pass tools

DESTRUCTIVE 3 tools

Destructive logi_delete_login_log Use when the user wants to remove a specific login record from view (e.g. 'delete that suspicious entry'). Sof Destructive logi_delete_passkey Use when the user explicitly asks to remove a specific passkey (e.g. lost device, old laptop). Destructive and Destructive logi_remove_redirect_uri Use when the user (RP owner) wants to deregister an old/unused OAuth callback URL — for example a historical o

WRITE 2 tools

Write logi_add_redirect_uri Use when the user (RP owner) wants to register a new OAuth callback URL — for example after deploying to a new Write logi_restore_login_log Use when the user wants to undo a deletion ('restore that log', 'I deleted the wrong one'). Takes an id from l

READ 10 tools

Read logi_fetch_quickstart Use when the user (or an agent) needs the logi/1pass agent quickstart guide — typical triggers: 'logi 어떻게 통합해? Read logi_get_doc Use when the user asks about a specific logi/1pass topic (OAuth scopes, PKCE, redirect URI rules, CLI commands Read logi_list_apps Use when the user (as a developer) asks 'what OAuth apps do I own?', 'list my RPs', or needs the app id before Read logi_list_connected_apps Use when the user asks 'which apps can see my data?', 'what have I authorized?', or wants to revoke third-part Read logi_list_docs Use when you (or the user) need to discover what logi/1pass docs exist — typically as a first step before logi Read logi_list_login_history Use when the user asks about recent sign-ins, suspicious access, login locations, or wants to audit account ac Read logi_list_passkeys Use when the user wants to see their registered Passkeys (Face ID / Touch ID / hardware key) — typically befor Read logi_list_trashed_logs Use when the user asks 'what did I delete?' or wants to review/restore previously soft-deleted login records. Read logi_show_app Use when the user wants the full RP record for one app (all fields: redirect_uris, app_link_url, allowed_scope Read logi_whoami Use when the user asks 'am I logged in?', 'which logi account is this?', or whenever you need to verify the co

EXPLORE

Related servers

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

FAQ

Questions about 1pass

Can an AI agent delete data through the 1pass MCP server? +

Yes. The 1pass server exposes 3 destructive tools including logi_delete_login_log, logi_delete_passkey, logi_remove_redirect_uri. 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 1pass? +

The 1pass server has 2 write tools including logi_add_redirect_uri, logi_restore_login_log. 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 1pass.

How many tools does the 1pass MCP server expose? +

15 tools across 3 categories: Destructive, Read, Write. 10 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on 1pass? +

Register the 1pass 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 1pass tool call.

Deterministic rules across all 15 1pass tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON 1PASS →

Instant setup, no code required.

15 1pass tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from 1pass's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →