mcpField
R
reminders-bridge

reminders-bridge

Remote
remindersbridge.vercel.appProductivity1Updated 4d ago

About reminders-bridge

RemindersBridge connects ChatGPT to Apple Reminders through a small agent running on the user's Mac. It supports reading and changing reminders while keeping reminder access on the Mac; a stateless relay passes requests and results between the connector and agent.

Key features

  1. 01Search and read reminders
  2. 02List reminder lists and items
  3. 03Create reminders with due dates
  4. 04Complete or reopen reminders
  5. 05Edit names, notes, and dates

Use cases

  1. 01Find a specific appointment reminder
  2. 02Add an item to a grocery list
  3. 03Mark a finished task complete
  4. 04Change a reminder's due date

MCP support

The hosted MCP endpoint connects to ChatGPT over OAuth and relays tool calls to the paired Mac agent, which executes them against Reminders.app. It exposes search, read, list, create, complete, and update tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://remindersbridge.vercel.app/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

✅ RemindersBridge

Use your Apple Reminders inside ChatGPT — through your own Mac.

License: MIT npm

RemindersBridge is a Model Context Protocol (MCP) connector that lets ChatGPT work with your Apple Reminders. Reads execute locally and requested results pass through the authenticated relay — every action runs on your own Mac through a tiny local agent. The cloud piece is only a stateless relay that shuttles requests between ChatGPT and your Mac.

  ChatGPT  ──OAuth──►  RemindersBridge relay  ──job queue──►  apple-reminders-agent  ──►  Reminders.app
 (connector)          (Vercel, stateless)      (your Mac, polls & executes)        (on your Mac)

Your Mac is the only place your reminders are ever read or written. The relay stores only short-lived job payloads and your account record; it never sees a reminder unless a job is in flight, and jobs expire in seconds.


For users — 3 steps

1. Create your account at remindersbridge.vercel.app and generate a pairing code.

2. Install the Mac agent (needs Node 18+):

npx apple-reminders-agent pair <YOUR-CODE>   # link this Mac to your account
npx apple-reminders-agent install            # keep it running on every restart

The first time it touches Reminders, macOS asks "Terminal wants to control Reminders" — click OK (one time).

3. Connect ChatGPT: Settings → Plugins → turn on Developer mode (Security & login) → Create a custom plugin → paste the MCP Server URL https://remindersbridge.vercel.app/mcp → Authentication OAuth → sign in & Allow.

That's it. In a new chat: "Search my Apple Reminders for the dentist appointment" or "Add oat milk to my Groceries list, due tomorrow."

Your Mac must be awake with the agent running. npx apple-reminders-agent install makes it start automatically at login and restart if it ever crashes.

Managing the agent
npx apple-reminders-agent status      # is it paired & reachable?
npx apple-reminders-agent logs        # recent activity
npx apple-reminders-agent uninstall   # stop auto-start

What ChatGPT can do

ToolAction
searchSearch reminders by keyword
fetchFetch full details of one reminder by id
list_listsList all reminder lists with open (incomplete) counts
list_remindersList reminders (optionally filter to one list, or include completed)
get_reminderRead a reminder by id or name
create_reminderCreate a reminder (name, optional notes, due date, target list)
complete_reminderMark a reminder complete (or reopen it)
update_reminderEdit a reminder's name, notes, or due date

Self-hosting

You can run your own relay so nothing depends on the hosted instance.

Prereqs: a Vercel account and a Supabase project (free tiers are fine).

  1. Storage — in your Supabase project's SQL editor, run supabase/schema.sql. It creates a tiny Redis-shaped KV + queue surface (nb_* functions) with RLS on.
  2. Deploy the server/ directory to Vercel.
  3. Set env vars (see server/.env.example):
    • SUPABASE_URL, SUPABASE_SERVICE_ROLE_KEY — your project + service-role key
    • JWT_SECRET — openssl rand -hex 32
  4. Verify: curl https://YOUR-APP.vercel.app/api/health → redisConfigured, redisOk, jwtSecretSet all true.
  5. Point the agent at it: npx apple-reminders-agent pair <CODE> --server https://YOUR-APP.vercel.app.

How it works

  • Auth — OAuth 2.1 with PKCE and Dynamic Client Registration (RFC 7591). ChatGPT registers itself, the user signs in on the RemindersBridge consent page, and ChatGPT gets a scoped MCP access token. JWTs are HMAC-signed; three kinds (session, agent, mcp) with distinct privileges. Optional email verification via Resend (RESEND_API_KEY); off unless configured, and enforcement is opt-in (REQUIRE_EMAIL_VERIFICATION).
  • Relay — MCP tool call → job pushed to jobs:<user> (TTL ≤ the caller's wait window, so an abandoned job can't run late) → the Mac agent (holding a hanging long-poll) is handed the job within ~200ms, executes it, pushes the result → the MCP handler returns it. The long-poll means jobs are delivered on arrival rather than on a fixed interval, so relay overhead is ~300ms instead of ~1s. The agent is considered "online" only while it's actively connected.
  • Agent — a dependency-free Node CLI. Tools run via JXA (osascript -l JavaScript) against Reminders.app; arguments are passed as JSON over argv (never shell-interpolated). A macOS LaunchAgent keeps it alive across logins and crashes.

Repository layout

server/    Vercel functions: OAuth + MCP endpoint + relay        (deploy this)
agent/     apple-reminders-agent — the npm-published Mac CLI          (users npx this)
kit/       Browser automations: register the dev-mode connector AND
           fill the OpenAI directory submission (see kit/README.md)
supabase/  schema.sql for self-hosting the storage
test/      end-to-end OAuth + MCP integration test

Development

# server
cd server && cp .env.example .env.local   # fill in, then: vercel dev
# end-to-end test against a live deployment (reads ../.env.local)
node test/e2e-oauth.mjs
# agent unit tests
node --test agent/test-agent-unit.mjs

Security & privacy

  • Reminders are read/written only on your Mac. The relay temporarily stores requested content in short-lived job/result queues — job payloads live in Redis-shaped storage with a short TTL and are deleted on delivery.
  • The agent token is stored at ~/.remindersbridge-agent.json (mode 600).
  • No secrets are committed; see .gitignore and the .env.example files.
  • Write tools are marked destructive so ChatGPT asks before changing a reminder.

License

MIT © Isaiah Dupree

Production storage and owner verification

Relay 1.4 uses isolated service-role-only tables/functions on the configured shared Supabase project. Production refuses missing storage configuration, bounds RPC requests to ten seconds, and returns HTTP 503 when storage or signing configuration is unavailable. Apply the checked-in isolated-storage migration before deploying this version; it does not replace another bridge's account tables or functions.

node --env-file=.env.local test/live-storage.mjs verifies the actual persistent store, FIFO, expiry and counters using temporary integration keys. BRIDGE_SESSION_FILE=/private/owner-session.json BRIDGE_READ_TOOL=READ_TOOL node test/live-relay.mjs verifies the actual owner session, PKCE OAuth, hosted MCP and paired-Mac read; choose this bridge's inventory tool. No reviewer data counts as a live acceptance. Credentials and sessions belong outside Git.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.