imsg — fast, local iMessage for your terminal & MCP
Package brand: imsg-mcp · CLI/MCP: imsg / imsg-mcp · PyPI today: pip install mac-imsg (target PyPI: imsg-mcp).
Read, search, and send iMessage from your terminal — or expose it to Claude,
Cursor, VS Code, or any MCP client. Everything runs locally on your Mac:
no cloud, no login, no account. Reads open ~/Library/Messages/chat.db
read-only; sends go through Messages.app.
macOS only. iMessage lives in Apple's local chat.db and Messages.app —
there is no official API and no equivalent on Linux or Windows, so imsg
only runs on macOS. See Requirements for the Full Disk
Access setup every install needs.
Why another one? The hot path — decoding tens of thousands of
attributedBody typedstream blobs — is written in Rust (PyO3 + rusqlite),
so reads and searches over a large history are several times faster than the
pure-Python equivalent that other Messages servers use. Pure Python still ships
as a zero-dependency fallback, so it works even where the wheel doesn't.
Benchmark
Full-history search over a synthetic 50,000-message database (70% stored as
attributedBody blobs), best-of-5, Apple Silicon (16 cores):
| operation | pure-Python | Rust core | speedup |
|---|---|---|---|
| full-history search (decodes every message) | 120.9 ms | 35.7 ms | 3.4× |
| batched blob decode (allocation-bound) | 19.1 ms | 19.6 ms | 1.0× |
Two honest caveats, stated up front:
- Raw blob decoding is ~a wash — it's bound by allocating result strings, not CPU, so native code doesn't help. The win is in search, where Rust decodes and filters across all cores and returns only the matches.
- It's 3.4×, not 16×, because the SQLite read and result marshalling are serial on both sides; only the decode+match parallelizes. The gap widens on larger histories.
Reproduce: python bench/benchmark.py. Bonus: this search also finds
messages whose text lives in an attributedBody blob — which a plain
text LIKE query (used by Python-only Messages servers) silently misses.
Install
imsg is macOS-only. Pick one:
# Homebrew
brew install ml-lubich/tap/imsg
# pip
pip install mac-imsg
# uv (recommended) — provisions Python + the prebuilt wheel
uv tool install mac-imsg
# from a clone, building the Rust core yourself
git clone https://github.com/ml-lubich/imsg.git && cd imsg
uv tool install .
The PyPI package is
mac-imsg—imsg-mcp(the eventual target name) was already registered when this shipped. The installed commands are alwaysimsgandimsg-mcp, regardless of package name.
Requirements
- macOS. Reads live at
~/Library/Messages/chat.db; sends go through Messages.app AppleScript. Neither exists on Linux or Windows, so there's no cross-platform build. - Full Disk Access for whichever app runs
imsg:- System Settings → Privacy & Security → Full Disk Access.
- Add the app that will run it — your terminal (Terminal/iTerm/Ghostty) for the CLI, or your MCP client (Claude Desktop, Cursor, VS Code, Claude Code) for the server.
- Fully quit and reopen that app — the permission doesn't take effect until relaunch.
- Messages.app signed in and able to send a normal message (only needed
for
imsg send).
Run imsg doctor to check access and see which engine (Rust or Python) is live.
Specs live under docs/ (overview, architecture, design, API, testing).
CLI
imsg -h # commands (also: imsg <cmd> -h)
imsg doctor # check Full Disk Access + engine
imsg chats # recent conversations + their ids
imsg contacts # handles (numbers / emails) seen
imsg contacts -q 415 # filter handles by substring
imsg contacts -q Rivera # or by AddressBook display name
imsg read -c +14155551234 # recent messages with a contact
imsg read --chat 42 --limit 100 # a specific conversation
imsg search "dinner" # search message text
imsg attachments -c +14155551234 # list media/files with on-disk paths
imsg attachments -k audio # only audio (image / video / application too)
imsg download -k image -o ./media # copy media out to a folder
imsg send +14155551234 "on my way"
imsg send "Jordan Rivera" "on my way" # resolves to one contact, or errors
imsg version # installed package version
imsg agent schema # JSON schema of every stable command
imsg agent guide # markdown playbook for LLM agents
Every command accepts -h / --help with options, arguments, and examples
(agent-friendly); imsg help <command> prints the same thing.
MCP server
The imsg-mcp entry point speaks MCP over stdio. Add it to any client:
Claude Code
claude mcp add --transport stdio --scope user imsg -- imsg-mcp
Claude Desktop / Cursor (mcpServers) · VS Code (servers):
{ "mcpServers": { "imsg": { "command": "imsg-mcp" } } }
Tools exposed: check_access, get_recent_messages, search_messages,
list_chats, list_contacts, list_attachments, download_attachments,
send_message (the only one with a side effect).
Contacts by name
-q on contacts and a name argument to send both resolve against the
local AddressBook (~/Library/Application Support/AddressBook/Sources/*/AddressBook-v22.abcddb),
read directly and read-only — never via osascript/Contacts.app. send
only goes through when a name resolves to exactly one contact; an ambiguous
or unmatched name raises an error listing the candidates and sends nothing.
Attachments
attachments / download cover images, audio, video, and documents. Messages
already keeps these on disk under ~/Library/Messages/Attachments, so
downloading is a local copy — nothing is fetched over the network. --kind is a
mime-type prefix (image, audio, video, application). Existing files are
never overwritten (colliding names become -1, -2, …), and rows whose backing
file is missing — iCloud-only or pruned by Messages — are listed with exists: false and skipped on download rather than aborting the batch.
How it works
There is no official iMessage API. Every tool in this space does the same two
local things; imsg just does the heavy half in Rust:
| Operation | Mechanism | Engine |
|---|---|---|
| read / search / list | chat.db (SQLite, read-only) + typedstream decode |
Rust (imsgcore), Python fallback |
| send | AppleScript → Messages.app | Python (osascript) |
SQLite is the same C library everywhere, so the read speedup comes from doing
the per-message attributedBody decode and row marshalling natively instead of
in a Python loop. See bench/benchmark.py for the
methodology — both engines run identical queries over an identical synthetic
database, and the pure-Python column is the same algorithm Python-only servers
use.
Privacy & security
- All database connections are opened read-only (
mode=ro). - Nothing is uploaded, mirrored, or indexed off-device.
- Sending is isolated in one function, escapes its AppleScript inputs, and is the only operation that writes anything anywhere.
- Full Disk Access is broad — grant it only to apps you trust.
Development
git clone https://github.com/ml-lubich/imsg.git && cd imsg
uv venv && source .venv/bin/activate
uv pip install maturin
maturin develop # builds the Rust core + installs the package
uv pip install -e ".[dev]"
pytest # tests run on the pure-Python path (and Rust if built)
python bench/benchmark.py # regenerate the benchmark
License
MIT © ml-lubich. Not affiliated with Apple. Use responsibly and only with accounts and conversations you own.
Metadata
Release files for imsg-mcp 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| imsg_mcp-0.1.3.tar.gz | 27.1 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| imsg_mcp-0.1.3-cp310-abi3-macosx_11_0_arm64.whl | CPython 3.10 | abi3 | macOS 11.0+ ARM64 | Details |
Total release size: 1.2 MB
Release files / imsg_mcp-0.1.3.tar.gz
| Download URL | imsg_mcp-0.1.3.tar.gz |
|---|---|
| Size | 27.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
20619389d218d9b015285bf4af0560b9d0a3cb66275dfa2fee02d64a56354df1
|
|
BLAKE2b-256 checksum How to use checksums |
aca14e2d6179dc2d0e0e13a2d0cdf0218ff0801f23bcd8bb83bf47cbf65a2a5b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.9
|
Release files / imsg_mcp-0.1.3-cp310-abi3-macosx_11_0_arm64.whl
| Download URL | imsg_mcp-0.1.3-cp310-abi3-macosx_11_0_arm64.whl |
|---|---|
| Size | 1.2 MB |
| Tags | CPython 3.10 abi3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
b343958a0f86ad97307327faebf9d408657e2841c0053cd66407aaf3a9e4ab18
|
|
BLAKE2b-256 checksum How to use checksums |
74e30988877bedd5ffcbf92ef2a07f5214f1a276d0cf34ae5bd278a25409f345
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.9
|
Security for imsg-mcp 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.