PluginBench
MCP Server
Maintained
Apache-2.0

io.github.CakeRepository/1password MCP Server

io.github.CakeRepository/1password

Secure 1Password vault access for AI agents—manage credentials without exposing secrets in chat.

What is the io.github.CakeRepository/1password MCP server?

The 1Password MCP Server is a Model Context Protocol server that gives Claude, Cursor, and other AI agents secure access to 1Password vaults and credentials through a service account. It provides 15 typed tools for discovering, reading, creating, and rotating secrets while keeping plaintext out of model transcripts via op:// references and op_run.

This server bridges your AI assistant to 1Password, letting you manage automation credentials, rotate passwords, and run commands with injected secrets—all without pasting plaintext into chat. It's built for teams that want least-privilege automation: create a dedicated service account, grant it only the vaults you need, and let the AI handle credential workflows securely.

How to install io.github.CakeRepository/1password

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • OP_SERVICE_ACCOUNT_TOKEN
    secret

    The Service Account Token from 1Password (required unless OP_KEYCHAIN_SERVICE is used on macOS)

  • OP_KEYCHAIN_SERVICE

    macOS only: Keychain service name to read the 1Password service account token from when OP_SERVICE_ACCOUNT_TOKEN is not set

  • OP_KEYCHAIN_ACCOUNT

    macOS only: Optional Keychain account name to narrow the lookup used with OP_KEYCHAIN_SERVICE

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "1password": {
      "command": "npx",
      "args": [
        "-y",
        "@takescake/1password-mcp"
      ],
      "env": {
        "OP_SERVICE_ACCOUNT_TOKEN": "<YOUR_OP_SERVICE_ACCOUNT_TOKEN>",
        "OP_KEYCHAIN_SERVICE": "<YOUR_OP_KEYCHAIN_SERVICE>",
        "OP_KEYCHAIN_ACCOUNT": "<YOUR_OP_KEYCHAIN_ACCOUNT>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • vault_list — List vaults the service account can access (id, name, description, type).
  • item_lookup — Search a vault by title substring with optional limit (max 200).
  • item_list — List every item in a vault (id, title, category, tags, updatedAt)—never secrets.
  • item_get — Retrieve full item metadata; concealed values hidden by default unless reveal: true. Accepts op://… or vault/item IDs.
  • password_read — Read one field (default password) via op://… or IDs. Metadata-only unless reveal: true.
  • op_check_ref — Validate op://vault/item/field and return non-secret metadata only.
  • password_create — Create a Login or Password item with username, URL, tags, notes.
  • note_create — Create a Secure Note with optional tags and custom fields.
  • password_update — Rotate a password or concealed field.
  • item_edit — Update title, notes, tags, URL; upsert or remove fields.
  • password_generate — Cryptographically secure random password (length 8–128, configurable symbols/numbers/uppercase).
  • password_generate_memorable — Memorable passphrase from ~500-word list with configurable word count, separator, and suffixes.
  • op_run — Run a local command with environment variables; op://… references resolved in child process only, secrets redacted from output.
  • item_archive — Move an item to the archive (hidden from normal views).
  • item_delete — Permanently delete an item—cannot be undone.

Use cases

  • Rotate automation credentials (database passwords, API tokens) without exposing them in chat
  • Run CI/CD commands with injected secrets from 1Password, keeping plaintext out of logs
  • Audit a vault by category and flag duplicates without revealing secret values
  • Generate and store secure passwords for new automation accounts
  • Verify op://vault/item/field references before using them in workflows

io.github.CakeRepository/1password MCP server FAQ

What is the 1Password MCP Server?

It's a community-built MCP server that connects your AI assistant (Claude, Cursor, etc.) to 1Password via a service account. You get 15 tools to discover, read, create, and rotate secrets—all while keeping plaintext out of model transcripts.

Is it free?

Yes. The server is open-source (Apache 2.0). You need a 1Password account with service account support (available on most 1Password plans).

How do I install it in Cursor or Claude Desktop?

Add the server to your MCP config with your service account token in the env. For Claude Desktop, edit ~/.config/Claude/claude_desktop_config.json; for Cursor, use the MCP settings UI. Restart the app and ask in plain English.

Do I need to reveal secrets to the AI?

No. The server defaults to hiding secret values. Use op_run to inject secrets into commands without revealing them, or op_check_ref to validate references. Reveal only when the human explicitly asks.

What authentication does it require?

A 1Password service account token. You create this in your 1Password web account under Developer → Service Accounts. Store it in an env var or macOS Keychain—never in config files.

Can I limit which vaults the AI can access?

Yes. Set OP_MCP_ALLOWED_VAULTS to a comma-separated list of vault names or IDs. This restricts op_run and op_check_ref to those vaults only.

README (reference)

Source of truth, from the repository.

1Password MCP Server

CI npm Node MCP License

Give your AI assistant a locked door to 1Password — not a pile of passwords in the chat.

@takescake/1password-mcp is a community Model Context Protocol (MCP) server. It lets Claude, Cursor, VS Code Copilot, OpenAI Codex, Gemini, and other MCP clients manage vaults and credentials through a 1Password Service Account.

Built on the MCP TypeScript SDK v2 with protocol negotiation for 2026-07-28 (and legacy clients). Secrets stay in 1Password; agents prefer op:// references and op_run so plaintext never has to land in the model transcript.

Not an official 1Password product. Community-built, Apache 2.0 licensed.


Who this is for

You are…You get…
Not deeply technicalA one-time setup: create a service account, paste the token into your AI app’s MCP settings, then ask in plain English (“list my automation vault”, “rotate the staging DB password”).
An agent / LLMFifteen typed tools, four workflow prompts, three browsable resources, and clear rules: prefer op_run + op:// over revealing secrets.
A developer / SREFull item CRUD, secure notes, password generation, vault allow-lists, Keychain token loading on macOS, and CI-friendly env config.

Why teams pick this server

  • Security-first defaults — password_read and item_get return metadata unless you opt in with reveal: true.
  • op_run (the MCP equivalent of op run) — inject op://vault/item/field into a local command’s environment; plaintext is redacted from stdout/stderr and never logged back to the model.
  • Full vault toolkit — list, search, get, edit, create logins & notes, rotate passwords, archive, or delete.
  • Guided prompts — password generation, credential rotation, vault audit, and secret-reference helpers.
  • Browsable resources — vault and item catalogs over 1password://… URIs (no secrets in resource payloads).
  • Modern MCP — stdio transport, Zod 4 schemas, MCP 2026-07-28 negotiation with legacy client compatibility.

What you get

Tools (15)

Grouped the way agents and humans actually use them.

Discover

ToolWhat it does
vault_listList vaults the service account can access (id, name, description, type).
item_lookupSearch a vault by title substring; optional limit (max 200).
item_listList every item in a vault (id, title, category, tags, updatedAt) — never secrets.

Read (safe by default)

ToolWhat it does
item_getFull item: title, category, tags, notes, fields. Concealed values stay hidden unless reveal: true. Accepts op://… or vaultId + itemId.
password_readRead one field (default password) via op://… or ids. Metadata-only unless reveal: true. Prefer op_run to use a secret.
op_check_refValidate op://vault/item/field and return non-secret metadata only (vault, item, field). Never the value.

Create & update

ToolWhat it does
password_createCreate a Login or Password item (username, URL, tags, notes). returnSecret defaults to false.
note_createCreate a Secure Note with optional tags and custom fields.
password_updateRotate a password / concealed field (creates the field if missing).
item_editUpdate title, notes (empty string clears), tags, URL; upsert or remove fields. Unreferenced fields stay untouched.
password_generateCryptographically secure random password (length 8–128; symbols/numbers/uppercase toggles).
password_generate_memorableMemorable passphrase from a ~500-word list (word count, separator, number/symbol suffixes).

Use secrets without revealing them

ToolWhat it does
op_runRun a local command (command or argv) with env vars. Values matching op://… are resolved into the child process only; resolved secrets are redacted from returned output. Optional cwd, shell, timeout_ms, stdin.

Soft-delete & destroy

ToolWhat it does
item_archiveMove an item to the archive (hidden from normal views).
item_deletePermanently delete an item — cannot be undone.

Prompts (4)

PromptWhen to use it
generate-secure-passwordGenerate (random or memorable) and optionally store — without dumping the password into chat.
credential-rotationFind → verify access → generate → update → confirm op:// reference.
vault-auditInventory a vault by category; flag duplicates / oddities — never reveal secrets.
secret-reference-helperBuild a paste-ready op://vault/item/field from names.

Resources (3)

URIContents
1password://configNon-secret server config (name, version, log level, token source, Node version).
1password://vaultsJSON list of accessible vaults.
1password://vaults/{vaultId}/itemsJSON item metadata for one vault (no secret values).

Before you start

You need two things:

  1. Node.js 20 or newer
  2. A 1Password Service Account with access to the vault(s) you want the AI to use

Create a service account (plain English)

  1. Sign in to your 1Password account on the web.
  2. Open Developer → Service Accounts (or follow 1Password’s guide).
  3. Create a service account and grant it only the vaults you want automation to touch (for example an Automation or CI vault — not your personal banking vault).
  4. Copy the token once. Treat it like a master key.

Quick start

Claude Desktop / Cursor / VS Code / most IDEs

Add this to your MCP config (exact file depends on the app):

{
  "mcpServers": {
    "1password": {
      "command": "npx",
      "args": ["-y", "@takescake/1password-mcp"],
      "env": {
        "OP_SERVICE_ACCOUNT_TOKEN": "YOUR_SERVICE_ACCOUNT_TOKEN"
      }
    }
  }
}

Restart the app, then try: “List my 1Password vaults.”

macOS Keychain (no token in the config file)

Store the token in Keychain, then point the server at it:

{
  "mcpServers": {
    "1password": {
      "command": "npx",
      "args": ["-y", "@takescake/1password-mcp"],
      "env": {
        "OP_KEYCHAIN_SERVICE": "op-service-account-claude-automation",
        "OP_KEYCHAIN_ACCOUNT": "your-macos-username"
      }
    }
  }
}

Token resolution order: CLI (--service-account-token / --token) → OP_SERVICE_ACCOUNT_TOKEN → macOS Keychain. OP_KEYCHAIN_ACCOUNT is optional when the service name alone is unique.

OpenAI Codex (TOML)

Option A — token in config:

[mcp_servers."1password"]
command = "npx"
args = ["-y", "@takescake/1password-mcp"]

[mcp_servers."1password".env]
OP_SERVICE_ACCOUNT_TOKEN = "YOUR_SERVICE_ACCOUNT_TOKEN"

Option B (recommended) — config only names the env var:

[mcp_servers."1password"]
command = "npx"
args = ["-y", "@takescake/1password-mcp"]
env_vars = ["OP_SERVICE_ACCOUNT_TOKEN"]

Set OP_SERVICE_ACCOUNT_TOKEN in your shell or CI. Note: codex mcp add ... --env OP_SERVICE_ACCOUNT_TOKEN=... writes the secret into Codex config; prefer env_vars when you can.

On macOS you can omit the token env and use OP_KEYCHAIN_SERVICE (+ optional OP_KEYCHAIN_ACCOUNT) instead.

Optional: lock op_run / op_check_ref to certain vaults

By default those tools may resolve op:// references from any vault the service account can see. To allow-list vaults:

{
  "env": {
    "OP_SERVICE_ACCOUNT_TOKEN": "YOUR_SERVICE_ACCOUNT_TOKEN",
    "OP_MCP_ALLOWED_VAULTS": "Automation, CI"
  }
}

Names or IDs work. References outside the list are rejected before resolution. Same setting via --allowed-vaults.


For agents: how to handle secrets

Follow this order every time:

  1. Discover with vault_list → item_lookup / item_list (metadata only).
  2. Confirm a reference with op_check_ref — never reveal just to see if a path exists.
  3. Use a secret in a command or API call with op_run and op://vault/item/field in env.
  4. Reveal with password_read / item_get + reveal: true only when the human explicitly needs the value in chat.
  5. Rotate with password_generate → password_update (keep returnSecret: false unless asked).
  6. Prefer item_archive over item_delete unless permanent removal is required.

op_run sketch

{
  "argv": ["curl", "-sS", "https://api.example.com/health"],
  "env": {
    "API_TOKEN": "op://Automation/Example API/credential"
  },
  "timeout_ms": 60000
}

Prefer argv over a shell command string when you can — fewer quoting surprises.


Configuration reference

Environment variables

VariableRequiredDescription
OP_SERVICE_ACCOUNT_TOKENUsually yesService account token. Not required on macOS if Keychain vars are set.
OP_KEYCHAIN_SERVICENomacOS: Keychain service name for the token.
OP_KEYCHAIN_ACCOUNTNomacOS: optional account to narrow the Keychain lookup.
OP_MCP_ALLOWED_VAULTSNoComma-separated vault names/IDs allowed for op_run / op_check_ref. Empty = unrestricted.
OP_INTEGRATION_NAMENoName reported to the 1Password SDK (default: 1password-mcp).
OP_INTEGRATION_VERSIONNoVersion reported to the SDK (default: package version).
MCP_LOG_LEVELNodebug | info | warn | error (default: info).
MCP_DEBUGNoIf set, forces debug logging.

CLI flags

--service-account-token <token>   1Password service account token
--token <token>                   Alias for --service-account-token
--log-level <level>               error | warn | info | debug (default: info)
--integration-name <name>         Custom integration name for the 1Password SDK
--integration-version <version>   Custom integration version
--allowed-vaults <list>           Comma-separated allow-list for op_run / op_check_ref

Security & privacy

Read this before pointing the server at a vault you care about.

  • LLM privacy — Anything revealed to the model may be sent to your AI provider and retained under their policies.
  • MCP is not end-to-end encrypted for secrets in flight — Values are plaintext inside the MCP workflow and toward the model. They are encrypted at rest in 1Password once stored.
  • Best fit — Automation credentials: CI tokens, bot accounts, disposable env secrets.
  • Avoid — Banking, primary personal logins, recovery codes, or anything you cannot afford to expose to a model provider.
  • Token = master key — Scope the service account tightly; rotate immediately if leaked; never commit tokens or MCP configs with secrets.
  • Prefer references — op://… + op_run beat pasting passwords into prompts or files.
  • Least privilege — Dedicated automation vaults beat sharing your whole account.

Protocol & compatibility

PieceDetail
Package@takescake/1password-mcp
RuntimeNode.js ≥ 20
Transportstdio
MCP SDK@modelcontextprotocol/server v2
ProtocolNegotiates 2026-07-28; keeps legacy client compatibility
Registry nameio.github.CakeRepository/1password

Development

git clone https://github.com/CakeRepository/1Password-MCP.git
cd 1Password-MCP
npm ci
npm run build
npm test
npm run lint

Watch mode: npm run dev.

Project layout

src/
  index.ts                 # Entrypoint — MCP stdio + protocol negotiation
  config.ts                # CLI / env / Keychain / allow-list
  client.ts                # 1Password SDK client
  logger.ts                # Structured logs on stderr (stdout is protocol)
  secret-ref.ts            # op:// parsing & allow-list checks
  utils.ts                 # Result helpers, password generation
  tools/                   # All 15 MCP tools
  prompts/                 # Interactive workflow prompts
  resources/               # 1password:// resources
tests/

See CONTRIBUTING.md. Maintainers / agents: AGENTS.md.


Changelog

See CHANGELOG.md for version history, including the 4.0.0 MCP v2 / 2026-07-28 migration and the 3.0.0 op_run / reveal-opt-in security changes.


License

Apache License 2.0

Related MCP servers

Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON.

Disposable private vector search + semantic RAG for AI agents. x402 pay-per-call, no account.

View repository →

Community-built, comprehensive MCP server for the SecurityScorecard API (unofficial).

0
TypeScript
View repository →

Local-first AI memory with causal graphs. Fully offline, zero config, your data stays local.

View repository →

CapMonster Cloud MCP server — AI captcha solver for reCAPTCHA, Turnstile & DataDome for AI agents.

1
Python
MIT
View repository →

Browser automation MCP for solving captchas with CapMonster Cloud via Patchright.

1
TypeScript
MIT
View repository →