Connect
FreeNot checkedA dead simple MCP server for exposing your app functions to AI agents like Claude Desktop.
About
A dead simple MCP server for exposing your app functions to AI agents like Claude Desktop.
README
Dead simple MCP (Model Context Protocol) server for exposing your app functions to AI agents
🚀 Claude Desktop Setup (5 Minutes)
Step 1: Install mcp-connect
npm install -g @myatkyawthu/mcp-connect
Step 2: Create mcp.config.js
Step 2: Create Your MCP Server
# Navigate to your project directory
cd your-project
# Generate sample config
mcp-connect init
This creates mcp.config.js with example tools:
import { defineMCP } from "@myatkyawthu/mcp-connect";
export default defineMCP({
name: "My MCP App",
version: "1.0.0",
tools: [
["hello", async ({ name = "World" }) => `Hello ${name}!`],
["echo", async ({ message }) => `Echo: ${message}`]
]
});
Step 3: Test Locally
Step 3: Configure Claude Desktop
Open Claude Desktop config file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Add your MCP server:
{
"mcpServers": {
"my-app": {
"command": "mcp-connect",
"args": ["C:/full/path/to/your/mcp.config.js"]
}
}
}
Important: Use the full absolute path to your mcp.config.js file.
Step 4: Start & Test
- Restart Claude Desktop completely
- Test connection: Ask Claude "What tools do you have available?"
- Use your tools: Try "Hello there!" or "Echo this message"
✅ Done! Your functions are now available to Claude Desktop.
📖 Tool Definition Guide
Simple Format (Recommended)
// Just name and function
["toolName", async (args) => "result"]
🔧 CLI Usage
Advanced Format (With Validation)
{
name: "toolName",
description: "What this tool does",
schema: {
type: "object",
properties: {
param: { type: "string", description: "Parameter description" }
},
required: ["param"]
},
handler: async ({ param }) => `Result: ${param}`
}
🛠 Development Commands
# Start with auto-reload during development
npm run dev
# Start server with specific config file
mcp-connect /path/to/your/mcp.config.js
# Format code
npm run format
# Lint code
npm run lint
🔧 Troubleshooting
Config File Not Found
# Create sample config
mcp-connect init
Claude Desktop Not Connecting
- Check config file path is absolute
- Restart Claude Desktop completely
- Check Claude Desktop logs for errors
Tool Not Working
- Verify tool syntax in
mcp.config.js - Check server logs for errors
- Test with simple tools first
📋 Examples
File Operations
["readFile", async ({ path }) => {
const fs = await import('fs/promises');
return await fs.readFile(path, 'utf8');
}]
API Calls
["getWeather", async ({ city }) => {
const response = await fetch(`https://api.weather.com/${city}`);
return await response.json();
}]
Database Queries
["getUser", async ({ id }) => {
// Your database logic here
return { id, name: "John Doe", email: "[email protected]" };
}]
🌐 Other MCP Clients
Claude Desktop setup is covered above. Tutorials for other MCP clients coming soon:
- VS Code extensions
- Custom applications
- Other AI platforms
📄 License
MIT © myat-kyaw-thu
Install Connect in Claude Desktop, Claude Code & Cursor
unyly install mcp-connectInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add mcp-connect -- npx -y @myatkyawthu/mcp-connectFAQ
Is Connect MCP free?
Yes, Connect MCP is free — one-click install via Unyly at no cost.
Does Connect need an API key?
No, Connect runs without API keys or environment variables.
Is Connect hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Connect in Claude Desktop, Claude Code or Cursor?
Open Connect on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzCompare Connect with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
