Agent Outbox
Drafts and manages personalized iMessage batches for review and approval, including contact lookup and message editing, while sending only after Touch ID approval through Messages.app.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Agent Outbox
Let AI agents draft your iMessages, but never send them. Claude Code, or any other MCP client, writes drafts and personalised batches (from a spreadsheet, a vCard file or your contacts) into a dashboard on your own Mac. You read them, edit them and approve with Touch ID. Only then does a small separate program, the executor, send them through Messages.app. Everything runs locally: no server, account or cloud service.
The gate holds even when the agent is confused or prompt-injected: there is no send tool, no send API and no approve call for an agent to use, and the executor refuses anything not signed with your passkey.

How it works
The agent calls
outbox_*MCP tools (or theoutboxCLI). They can only create and edit drafts.You open
http://localhost:7477, review each message, edit or skip any, and press Approve.Touch ID signs a manifest listing every message's recipient and the SHA-256 of its exact text.
The executor checks the signature and that every message still matches, then hands it to Messages.app. A message edited after approval no longer matches and needs a new approval.
Related MCP server: MessagesBridge
Requirements
macOS 14 or newer, Apple silicon or Intel
Bun (
brew install oven-sh/bun/bun)Xcode Command Line Tools (
xcode-select --install)Messages signed in to your Apple ID (for SMS to non-iPhones, turn on Text Message Forwarding on your iPhone)
Safari or Chrome. Macs without Touch ID unlock the passkey with your Mac password, or with your phone.
Install
Let your agent do it. Paste this into Claude Code (or any coding agent):
Set up Agent Outbox on this Mac: clone https://github.com/ay2609/agent-outbox (or pull it if I already have it), read its README and run ./install.sh. Never use sudo. When it finishes, give me the setup link it printed and stop: I create the passkeys with Touch ID myself. Don't open that link, don't edit anything in ~/Library/Application Support/agent-outbox, don't run the harden command and don't turn on live sending. Then tell me to start a new session so the agent-outbox MCP tools load. From then on, draft messages with the outbox_* tools for me to approve in the dashboard; you can't send, so don't try.Or by hand:
git clone https://github.com/ay2609/agent-outbox.git
cd agent-outbox
./install.shThe installer builds the dashboard and the executor, starts two per-user LaunchAgents, and registers the agent-outbox MCP server with Claude Code if claude is installed. It never uses sudo; re-running it upgrades. Options: --port N, --no-mcp, --dry-run, --setup-link, --help.
First run
Open the setup link the installer printed (
http://localhost:7477/#/setup?token=…). Lost it?./install.sh --setup-link.Create the two passkeys it asks for: one to sign in, one to approve sending.
You start in dry mode: approved messages are written to
~/Library/Application Support/agent-outbox/logs/dry-sends.jsonland nothing is sent. Ask your agent to draft a text and try it.
Simple and hardened mode
Simple mode (the default) keeps your approval keys in a file you own. That stops an agent using its tools, and prompt injection, from sending anything. It does not stop a program running as you, outside a sandbox, from planting its own key in that file.
Hardened mode moves the keys to a root-owned file, /Library/Application Support/agent-outbox/passkeys.json, and the executor then trusts only that. Settings > "Harden your install" shows the one sudo command. Run it yourself in Terminal; never let an agent run it. Do it before you rely on live sending, especially if an agent on this Mac has an unsandboxed shell.
Going live
Settings: tick "Allow live sending", then switch the transport to live (both ask for Touch ID).
On the first live send macOS asks whether "Agent Outbox" may control Messages, and on the first contacts sync it asks for Contacts. Allow both only for "Agent Outbox".
Send a first message to yourself.
Approved messages go out right away, 2 seconds apart. Stop halts everything and revokes unused approvals.
MCP tools
All draft-only.
Tool | Does |
| Find people in your contacts |
| One message |
| A batch, optionally from a template with per-recipient fields |
| Edit or cancel before approval |
| Status, including what was sent |
| Turn a CSV, XLSX, vCard or pasted table into a batch |
| Propose new contacts (added automatically after a duplicate check) or edits (wait for Touch ID) |
| Refresh the contact list |
Other MCP clients: run bun run <repo>/src/mcp/index.ts as a stdio server. The same API is available as a CLI: bun run cli --help.
Configuration
Optional ~/Library/Application Support/agent-outbox/config.json:
{ "port": 7477, "compose": "auto", "claude_path": "/abs/path/to/claude" }compose shows an "Ask Claude" box in the dashboard when claude is found ("off" hides it). Environment overrides: OUTBOX_HOME, OUTBOX_PORT. After changing the port, re-run ./install.sh.
Uninstall
./uninstall.sh # remove the services and MCP registration, keep your data
./uninstall.sh --purge # also delete ~/Library/Application Support/agent-outboxFAQ
Why not give the agent AppleScript? Then it can send anything, including text an attacker slipped into a file it read. Here the only program that can send checks a signature made with your finger.
Why does macOS ask for permission again after an update? The executor is ad-hoc signed, so each build is a new app to macOS. That's deliberate: a long-lived signing key on your Mac could sign a rogue app. If sends fail with error -1743, run tccutil reset AppleEvents io.github.ay2609.agent-outbox.exec and allow the prompt again.
Can it read my replies or send group messages? No and no.
Development
bun install && bunx tsc --noEmit -p . && bun test
bun run web:build
cd exec && ./build.sh && build/OutboxExec.app/Contents/MacOS/outbox-exec selftest
OUTBOX_HOME=$TMPDIR/ao OUTBOX_PORT=7478 bun run src/server.ts # dev server on a throwaway state dirNever weaken the send gate: no agent-facing tool may send, approve or change settings. Keep dry mode the default.
Acceptable use
Only send messages you'd send yourself, to people who expect to hear from you. No spam or unsolicited bulk texting. You're responsible for everything sent from your account, and bulk texting from a personal number can get your Apple ID flagged.
MIT licensed. Security reports: see SECURITY.md. Not affiliated with Apple; iMessage and Messages are Apple trademarks.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP connector for iMessage & Contacts via a local Mac agent + Vercel relay
MCP server for SuperPhone — contacts, conversations, tags and consent-based text messages.
Send and receive iMessage, SMS, RCS, and WhatsApp, and manage contacts, chats, and numbers.
Send and read iMessages from your own Mac and Apple ID — drafts, history and contacts.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables interaction with iMessage through a BlueBubbles server, allowing users to read, search, and send messages directly from MCP clients. It supports comprehensive chat management features including reactions, group chat moderation, message scheduling, and contact lookups.332MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that lets ChatGPT search and read iMessage/SMS history, send one-at-a-time messages, and manage Contacts on your own Mac, with confirmations for any writes.MIT
- AlicenseAqualityCmaintenanceLets MCP clients search iMessages, read Apple Notes including checklist state, and look up Contacts on macOS.12MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to send, receive, and react to iMessage texts on macOS, including inline replies and any-emoji tapbacks, with per-chat allowlisting and rate limits.Apache 2.0