NotesBridge
MCP server enabling ChatGPT to search, read, and write Apple Notes via a local Mac agent with a privacy-preserving relay.
README
<div align="center">
π NotesBridge
Use your Apple Notes from ChatGPT β search, read, and write, powered by your own Mac.
</div>
NotesBridge is a Model Context Protocol (MCP) connector that lets ChatGPT work with your Apple Notes. It never uploads your notes to a third party β 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 ββOAuthβββΊ NotesBridge relay ββjob queueβββΊ apple-notes-agent βββΊ Apple Notes.app
(connector) (Vercel, stateless) (your Mac, polls & executes) (on your Mac)
Your Mac is the only place your notes are ever read or written. The relay stores only short-lived job payloads and your account record; it never sees a note unless a job is in flight, and jobs expire in seconds.
For users β 3 steps
1. Create your account at notesbridge.vercel.app and generate a pairing code.
2. Install the Mac agent (needs Node 18+):
npx apple-notes-agent pair <YOUR-CODE> # link this Mac to your account
npx apple-notes-agent install # keep it running on every restart
The first time it touches Notes, macOS asks "Terminal wants to control Notes" β click OK (one time).
3. Connect ChatGPT: Settings β Plugins β turn on Developer mode (Security & login) β Create a custom plugin β paste the MCP Server URL https://notesbridge.vercel.app/mcp β Authentication OAuth β sign in & Allow.
That's it. In a new chat: "Search my Apple Notes for the Q3 planning note" or "Create a note titled Groceries with milk, eggs, coffee."
Your Mac must be awake with the agent running.
npx apple-notes-agent installmakes it start automatically at login and restart if it ever crashes.
Managing the agent
npx apple-notes-agent status # is it paired & reachable?
npx apple-notes-agent logs # recent activity
npx apple-notes-agent uninstall # stop auto-start
What ChatGPT can do
| Tool | Action |
|---|---|
search |
Search notes by keyword |
fetch / get_note |
Read a note's full content |
list_folders |
List folders with note counts |
list_notes |
List notes (optionally by folder) |
create_note |
Create a new note |
append_to_note |
Append text to a note |
update_note |
Rewrite a note (destructive β ChatGPT confirms first) |
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).
- Storage β 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. - Deploy the
server/directory to Vercel. - Set env vars (see
server/.env.example):SUPABASE_URL,SUPABASE_SERVICE_ROLE_KEYβ your project + service-role keyJWT_SECRETβopenssl rand -hex 32
- Verify:
curl https://YOUR-APP.vercel.app/api/healthβredisConfigured,redisOk,jwtSecretSetalltrue. - Point the agent at it:
npx apple-notes-agent pair <CODE> --server https://YOUR-APP.vercel.app.
How it works
- Auth β OAuth 2.1 with PKCE and Dynamic Client Registration (RFC 7591). ChatGPT registers itself, the user signs in on the NotesBridge 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 β MCP tool call β job pushed to
jobs:<user>(TTL β€ the caller's wait window, so an abandoned job can't run late) β the Mac agent (holding a hanging long-poll) is handed the job within ~200ms, executes it, pushes the result β 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 β a dependency-free Node CLI. Tools run via JXA (
osascript -l JavaScript) against Notes.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-notes-agent β 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
- Notes are read/written only on your Mac. The relay never persists note content β job payloads live in Redis-shaped storage with a short TTL and are deleted on delivery.
- The agent token is stored at
~/.notesbridge-agent.json(mode600). - No secrets are committed; see
.gitignoreand the.env.examplefiles. - Write tools are marked destructive so ChatGPT asks before overwriting.
License
MIT Β© Isaiah Dupree
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.