imessage-mcp
Read-only MCP server for your iMessage DB. No hosted service.
README
imessage-cli
A monorepo of three Python packages and a Next.js broker that turn your local iMessage history into something an MCP-capable AI (Claude, Cursor, Poke, …) can read — and optionally reply through — without your messages ever leaving your Mac.
Packages (published to PyPI)
| Package | Install | What it does |
|---|---|---|
imessage-mcp |
uv tool install imessage-mcp |
Read-only MCP server for your iMessage DB. No hosted service. |
imessage-mcp-send |
uv tool install imessage-mcp-send |
Adds a send_message tool. Irreversible writes. |
imessage-bridge |
uv tool install imessage-bridge |
Connected CLI with account-managed API keys and a stable broker URL. |
Each package has its own README inside packages/<name>/.
Architecture
Claude / Poke / Cursor (MCP client)
│
│ Bearer <api_key>
▼
Next.js broker (backend/) ◀── Supabase auth + Postgres
│ Bearer <tunnel_token>
▼
*.trycloudflare.com tunnel
│
▼
imessage-mcp on your Mac ◀── chat.db (read-only)
The broker is plumbing — your messages never leave your Mac.
Repository layout
packages/imessage-mcp/ ← published: read-only MCP server
packages/imessage-mcp-send/ ← published: optional send_message tool
packages/imessage-bridge/ ← published: connected CLI for the broker
backend/ ← Next.js + Supabase broker (not published)
src/imessage_cli/ ← legacy local-only tools (imessage-cli, imessage-ai)
The workspace is a uv workspace; packages share a single venv during dev.
Development setup
git clone https://github.com/moritzhwnr/imessage-cli
cd imessage-cli
uv sync # installs all three packages + legacy CLIs in editable mode
uv run imessage-mcp --help
uv run imessage-bridge --help
For the broker:
cd backend
cp .env.local.example .env.local # fill in Supabase URL + service-role key + encryption key
npm install
npm run dev # http://localhost:3000
See backend/supabase/migrations/0001_init.sql for the database schema and backend/.env.local.example for the required env vars.
License
MIT — see LICENSE.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.