DEV Community

fred
fred

Posted on

How to Turn Any App into an MCP Server with MCPify

#mcp #ai #tutorial #opensource

The AI landscape is shifting fast. Every week, a new agent framework, a new protocol, a new way for AI to interact with the world. But one thing has become painfully clear: most of our existing software was never built for AI agents to use.

You have a SaaS product, a REST API, a database, maybe a frontend with useful actions. An AI agent cannot touch any of it without brittle browser automation or hand-written boilerplate. That is where MCPify comes in.

MCPify is an open-source AI enablement compiler that transforms existing applications into AI-native, agent-operable systems. Instead of manually writing MCP server code for every tool you want an agent to use, you point MCPify at your codebase and it does the heavy lifting automatically.

In this tutorial, I will walk you through turning any app into an MCP server using MCPify --- no prior MCP experience required.

What Is MCP (Model Context Protocol)?

Before we dive in, a quick refresher. The Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools and data sources. Think of it as USB-C for AI agents --- a universal interface that lets any MCP-compatible client (Claude Desktop, Cursor, VS Code extensions, custom agents) talk to your services.

An MCP server exposes tools that an AI agent can discover, inspect, and invoke at runtime. Building these servers manually for each endpoint, database query, or business workflow is tedious and does not scale.

Enter MCPify: The MCP Server Generator

MCPify (https://github.com/amarnath3003/MCPify) is an AI enablement compiler that scans your application and automatically generates a complete MCP server. It works by performing static analysis on your codebase --- frontend components, backend routes, API definitions, event handlers, and workflow logic --- and compiling that into MCP-compatible tools.

Why MCPify stands out:

  • Zero manual tool writing --- it discovers tools from your code automatically
  • Permission-aware --- generated tools include safety boundaries so agents operate within safe limits
  • Stay in sync --- regenerate whenever your codebase changes; the MCP server is always up to date
  • CI/CD integration --- MCPify runs in your GitHub Actions pipeline, so every PR recompiles fresh tools
  • Swagger/OpenAPI support --- have an API spec? MCPify converts it to MCP tools in one command

If you have been searching for an MCP server generator that actually works, this is it.

Quick Start: No Install Required

MCPify ships as a CLI tool via npm. You do not even need to install it --- just run it directly with npx:

npx mcpify-cli
Enter fullscreen mode Exit fullscreen mode

This launches an interactive mode that guides you through analyzing your project. If you want to see it in action immediately, try it against the built-in ecommerce example:

npx mcpify-cli examples/ecommerce-saas
Enter fullscreen mode Exit fullscreen mode

Within seconds, MCPify scans the example app and generates a complete MCP server in the output directory. Open the generated AGENTS.md for instructions on connecting it to any MCP client.

Tutorial: MCPify Your Own App

Let us go step by step with a real-world scenario.

Step 1: Run the Analyzer

Navigate to your project root and run:

npx mcpify-cli analyze .
Enter fullscreen mode Exit fullscreen mode

The analyze command runs the full pipeline: scanning, compiling, and generating the MCP server along with metadata your agent needs.

Step 2: Choose Your Analyzers

MCPify uses pluggable analyzers to understand different parts of your stack:

  • Frontend analyzer --- extracts UI actions (button clicks, form submissions, navigation)
  • Backend analyzer --- discovers REST routes, middleware, and business logic
  • Database analyzer --- identifies schemas, queries, and stored procedures
  • Event analyzer --- captures event handlers and webhook listeners
  • Workflow analyzer --- maps multi-step processes your app supports

Use the interactive command to select which analyzers to run:

npx mcpify-cli interactive
Enter fullscreen mode Exit fullscreen mode

Step 3: Review the Generated MCP Server

After analysis, MCPify writes the generated server to your output directory (default: mcpify-output/). The server is a standalone Node.js application implementing the MCP specification. You will find:

  • server.js --- the MCP server entry point
  • tools.json --- a manifest of all discovered tools with their schemas
  • AGENTS.md --- setup instructions for connecting to MCP clients
  • workflows/ --- semantic workflow definitions discovered in your app

Step 4: Connect to an MCP Client

Follow the instructions in AGENTS.md. Typically this means adding the server to your client configuration. For Claude Desktop, you would add an entry to your claude_desktop_config.json:

{
  "mcpServers": {
    "my-app": {
      "command": "node",
      "args": ["path/to/mcpify-output/server.js"]
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Restart your client, and your AI agent can now interact with your application through natural language.

Advanced: Swagger/OpenAPI to MCP

Already have an API specification? MCPify can convert it directly:

npx mcpify-cli swagger ./openapi.yaml
Enter fullscreen mode Exit fullscreen mode

This is incredibly useful if you maintain a public API --- every endpoint becomes an MCP tool automatically, complete with request/response schemas.

CI/CD Integration

For teams that want this to be automatic, MCPify includes a GitHub Actions workflow. Every time you push to main or open a PR, MCPify recompiles your MCP server. This means your AI tools are never out of sync with your codebase.

Check the .github/workflows folder in the MCPify repo for a ready-to-use workflow template.

Why Developers Love MCPify

Since launching on GitHub, MCPify has been gaining traction (41 stars and rising) because it solves a real problem. Developers building AI agents need a way to connect those agents to existing infrastructure without months of integration work.

MCPify fits that gap perfectly. It is the MCPify alternative to hand-rolled MCP servers --- faster, more thorough, and automatically kept in sync.

If you are building agents and tired of writing tool definitions by hand, give MCPify a try:

👉 Try MCPify Now

Final Thoughts

The era of AI agents is here. The question is whether your software is ready for them. With MCPify, you can make any application agent-ready in minutes, not weeks.

The pattern is simple: write your app as you normally would, run MCPify, and let AI agents interact with it naturally. No boilerplate, no endless configuration files, no brittle browser automation.

Give it a spin with npx mcpify-cli and let me know what you build.

Found this useful? Share it with a friend building AI agents. The project is open-source on GitHub, contributions welcome!

Top comments (0)