mcpField
M
M1K3

M1K3

Local
m1k3.appMemory & Knowledge6Updated today

About M1K3

M1K3 is a Mac-native app for people who want private, on-device memory and AI for their agents. It combines local inference, voice, a personal knowledge graph, and an HTTP MCP server.

Key features

  1. 01On-device MLX inference
  2. 02Voice with Kokoro TTS and WhisperKit STT
  3. 03Personal knowledge graph with RAG
  4. 04Embedded agent and 3D companion
  5. 05Local document and knowledge access

Use cases

  1. 01Search personal knowledge for an agent
  2. 02Ask the resident AI through MCP
  3. 03Use voice to interact with the app

MCP support

The running app serves an MCP server over HTTP at `http://127.0.0.1:4242/mcp`. It exposes knowledge search, documents, voice, and `ask_m1k3`.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

M1K3 for macOS — build from source

The flagship surface: a Mac-native SwiftUI app — on-device MLX inference, live voice (Kokoro TTS + WhisperKit STT), a personal knowledge graph with RAG, an embedded agent, a 3D companion, and a local MCP server other agents can call.

Private by design. M1K3 runs on your Mac. Models download once from Hugging Face; after that the only network use is web search, which is on by default so answers can be current, with one switch in Settings to turn it off. (An opt-in Apple Private Cloud Compute rung arrives in a later release; the 1.0 build has no cloud path.)

Requirements

  • macOS 26 (Tahoe) on Apple Silicon — hard requirement: the app uses Liquid Glass, on-device Foundation Models, and Metal via MLX.
  • Xcode 26.x (Swift 6.2 toolchain).
  • XcodeGen and (optional, nicer logs) xcbeautify: brew install xcodegen xcbeautify
  • Disk: nothing to download for the default brain (Mini runs on Apple's on-device models). Allow ~2–7 GB extra only if you opt into the bigger Lil/Big brains.

Build & run

git clone https://github.com/Round-Tower/M1K3.git
cd m1k3/macos

# project.yml is the source of truth — M1K3.xcodeproj is generated, not tracked
xcodegen generate

open M1K3.xcodeproj    # then ⌘R (set your own dev team for local signing)

Or from the command line:

xcodebuild -scheme M1K3 -destination 'platform=macOS' build | xcbeautify
# The same package graph also drives the iOS + visionOS shell (M1K3iOSApp/):
xcodebuild -scheme M1K3iOS       -destination 'generic/platform=iOS Simulator'      build | xcbeautify
xcodebuild -scheme M1K3visionOS  -destination 'generic/platform=visionOS Simulator' build | xcbeautify

First launch is one screen: say hello (a name is optional) and you're talking — M1K3 starts on Mini, Apple's built-in on-device model, so there's nothing to download. Sharper local brains (Lil / Big) are one click away in Settings, or via the in-chat offer after your first answer; weights download only when you ask.

Signing note: run with your personal development team. Building with CODE_SIGNING_ALLOWED=NO compiles fine (CI does it) but the app then runs without its sandbox container and will read/write the wrong data locations.

Tests

The business logic lives in SwiftPM packages and tests without Xcode:

swift test --parallel --disable-xctest   # the full fast suite (CI runs it without the flag)
tools/dev/tdd.sh M1K3KnowledgeTests     # one test target, rebuilt and run alone

Tests use swift-testing (import Testing, @Test), not XCTest.

Heavy MLX/Metal integration tests are env-gated off by default — M1K3_MLX_INTEGRATION=1 swift test opts in (downloads a real model and generates; Apple Silicon only).

Where things are

M1K3App/macOS app shell: SwiftUI views, AppEnvironment, settings
M1K3iOSApp/iOS + visionOS SwiftUI shell (M1K3iOS/M1K3visionOS schemes) on the shared Sources/ graph
Sources/SwiftPM modules: agent, inference, knowledge/RAG, voice, MCP
Tests/swift-testing suites per module
project.ymlXcodeGen spec (the .xcodeproj is a build artifact)
ROADMAP.mdWhat's next — kept current
PLAN.mdHistorical build log / decision record (append-only, signed)
docs/ADRs, model choices, MCP setup, release pipeline

MCP server

The running app serves MCP over HTTP at http://127.0.0.1:4242/mcp — knowledge search, documents, voice, and ask_m1k3 (ask the resident AI). See docs/MCP_SETUP.md to wire it into Claude Code or any MCP client.

Contributing

See CONTRIBUTING.md at the repo root. Found a bug? In the app: Settings → Report an issue… generates a redacted diagnostic you can attach to a GitHub issue.

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.