mcp-server

kmsg

Unofficial KakaoTalk CLI and native MCP server for macOS — read, watch, and send messages via Accessibility automation.
278 stars+2★ this week48 forksSwiftUpdated 9/21/2026100% free · open source
What it does

kmsg is a command-line tool that allows you to read, watch, and send KakaoTalk messages on macOS via Accessibility automation.

When to use it
  • •Automating KakaoTalk messaging tasks for your startup
  • •Integrating KakaoTalk with other services or tools on macOS
  • •Building custom KakaoTalk-related workflows or bots
Ready-to-paste prompt
./kmsg send 'Hello from kmsg!'
Heads up: You need to enable Accessibility permissions for kmsg in System Preferences > Security & Privacy > Privacy > Accessibility, and also allow KakaoTalk to be controlled by kmsg
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/kmsg && curl -fsSL https://workflowstacks.com/api/skills/kmsg/claude-skill -o ~/.claude/skills/kmsg/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How kmsg works
Codeflow
Free to inspect

Kmsg is a large Swift project (~15k lines across 98 code files, plus 29 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit a month ago, MIT license, has a test suite.

Size
Large codebase
~15k lines · 98 code files · ~2 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Swift
No API keys detected
Swift 59%TypeScript 23%Python 11%JavaScript 5%CSS 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    skills/kmsg/SKILL.md
    Inside skills/ — an example of what the AI is told to do
What's in each folder
skills/Prompts, skills & agent definitions3 files
site/Frontend / UI99 files
Plugins/Sub-packages / plugins1 files
docs/Documentation3 files
Sources/Folder31 files
video/Folder24 files
tools/Helper scripts2 files
scripts/Helper scripts1 files
READMEHas testsDocumentedCI checksMIT licenseUpdated 1 mo ago
Quick Actions
Details
Creator
channprj
Language
Swift
Category
mcp-server
Published
1/29/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/kmsg.svg)](https://workflowstacks.com/skills/kmsg?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 370,019
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,544
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 133,734
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 4,022
Rapid-MLX: Supercharge Local AI on Apple Silicon
Rapid-MLX gives founders a lightning‑fast, OpenAI‑compatible engine for Mac M1/M2 chips—4.2× quicker than Ollama with instant tool calling. Ideal for AI‑driven product prototypes. 4.0k+ GitHub stars.
mcp-server★ 665
smg
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.
mcp-server★ 145
llm – Ruby AI Runtime for Building Agentic Apps Quickly
A lightweight Ruby library that lets founders embed LLM-powered agents and retrieval‑augmented generation into their products with minimal setup. Ideal for Ruby‑centric startups seeking AI capabilities.