# 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 the user before calling. Takes the passkey id from logi_list_passkeys.

Agent View of the PolicyLayer registry record for `logi_delete_passkey`. HTML page: https://policylayer.com/tools/1pass-mcp/logi-delete-passkey

## Facts

- Tool: `logi_delete_passkey`
- Server: 1pass (`@1pass/mcp`) — https://policylayer.com/tools/1pass-mcp.md
- Install: `npx -y @1pass/mcp`
- Homepage: https://github.com/dcode-co/logi-plugins
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Hidden

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | number | yes |  |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "logi_delete_passkey",
    "arguments": {
      "id": 0
    }
  }
}
```

## Why logi_delete_passkey is rated Critical

An AI agent that decides to call logi_delete_passkey doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from 1pass is gone. There is no undo for destructive operations.

## Use case

AI agents call logi_delete_passkey to permanently remove resources in 1pass, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 1pass:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "logi_delete_passkey"
  ]
}
```

## Other tools on 1pass (14)

- `logi_delete_login_log` — Destructive — https://policylayer.com/tools/1pass-mcp/logi-delete-login-log.md
- `logi_remove_redirect_uri` — Destructive — https://policylayer.com/tools/1pass-mcp/logi-remove-redirect-uri.md
- `logi_fetch_quickstart` — Read — https://policylayer.com/tools/1pass-mcp/logi-fetch-quickstart.md
- `logi_get_doc` — Read — https://policylayer.com/tools/1pass-mcp/logi-get-doc.md
- `logi_list_apps` — Read — https://policylayer.com/tools/1pass-mcp/logi-list-apps.md
- `logi_list_connected_apps` — Read — https://policylayer.com/tools/1pass-mcp/logi-list-connected-apps.md
- `logi_list_docs` — Read — https://policylayer.com/tools/1pass-mcp/logi-list-docs.md
- `logi_list_login_history` — Read — https://policylayer.com/tools/1pass-mcp/logi-list-login-history.md
- `logi_list_passkeys` — Read — https://policylayer.com/tools/1pass-mcp/logi-list-passkeys.md
- `logi_list_trashed_logs` — Read — https://policylayer.com/tools/1pass-mcp/logi-list-trashed-logs.md
- `logi_show_app` — Read — https://policylayer.com/tools/1pass-mcp/logi-show-app.md
- `logi_whoami` — Read — https://policylayer.com/tools/1pass-mcp/logi-whoami.md
- `logi_add_redirect_uri` — Write — https://policylayer.com/tools/1pass-mcp/logi-add-redirect-uri.md
- `logi_restore_login_log` — Write — https://policylayer.com/tools/1pass-mcp/logi-restore-login-log.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=1pass-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/1pass-mcp