mcp-server

lnwjud

lnwjud — local AI-agent runtime & MCP gateway
205 stars94 forksTypeScriptUpdated 10/17/2026100% free · open source
What it does

Runs a local AI‑agent runtime that exposes your agents through a MCP (Multi‑Channel Protocol) gateway, letting you call them via simple HTTP requests.

When to use it
  • •You want to prototype or test custom LLM‑driven agents on your laptop before deploying to the cloud.
  • •Your product needs a lightweight, self‑hosted endpoint that other services can call (e.g., Slack bot, internal tool).
  • •You need a unified MCP gateway to route requests to multiple agents from a single URL.
Ready-to-paste prompt
curl -X POST http://localhost:3000/agent/summary -H "Content-Type: application/json" -d '{"text":"Long article about remote work..."}'
Heads up: The gateway will refuse all calls until `MCP_API_KEY` in your `.env` matches a valid key registered in the MCP service; generate the key in the MCP console before starting the server.
Saves to your device
Use with Claude
New

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

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/lnwjud && curl -fsSL https://workflowstacks.com/api/skills/lnwjud/claude-skill -o ~/.claude/skills/lnwjud/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 lnwjud works
Codeflow
Free to inspect

Lnwjud is a very large TypeScript project (~213k lines across 808 code files, plus 185 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~213k lines · 808 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app — add your API keys. Reading the code is optional.
Runs on
Node.js
Needs API keys (.env)
TypeScript 88%PowerShell 4%JavaScript 3%Rust 1%Swift 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
    package.json
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
What's in each folder
packages/Sub-packages / plugins603 files
apps/Sub-packages / plugins346 files
docs/Documentation63 files
recipes/Examples you can copy4 files
native/Folder43 files
scripts/Helper scripts37 files
tests/Tests — proof it works36 files
assets/Images & static assets25 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
engasnm111
Language
TypeScript
Category
mcp-server
Published
8/10/2026

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/lnwjud.svg)](https://workflowstacks.com/skills/lnwjud?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.