Public alpha · v1.0.0-alpha.2

AI-ready your software
in minutes.

Open source platform to expose any API as a Model Context Protocol (MCP) server. CLI-first, type-safe, edge-deployable. Your handler stays a one-liner — auth, rate limits, schema validation and deploy live in the framework.

Get started Star on GitHub

$ npx @mcify/cli@alpha init my-mcp

Why mcify

Six things you'd build by hand the first week — already in the box.

Type-safe end-to-end

One Zod schema becomes your handler types, JSON Schema for tools/list, and a generated client. No drift between server, client, and docs.

Edge-first

Same handler runs on Cloudflare Workers, Vercel Edge, Bun, Node, or Docker. The runtime ships adapters for each — no rewrites.

AI-agent-aware

mcify init ships an AGENTS.md that Claude Code, Cursor, Cody and Copilot Workspace read automatically. Your agent already knows the conventions.

Built-in inspector

mcify dev opens a local web inspector at :3001 — list of tools, live calls log, playground to invoke by hand. No extra setup.

Composable middleware

requireAuth, rateLimit, withTimeout ship in core. Wrap any tool. Write your own; they compose like Express/Hono.

Deploy in one command

mcify deploy cloudflare, vercel, or docker. Bundles, generates config, deploys. Pre-flight size checks for edge runtimes.

Define a tool. See it live.

Schemas double as runtime validation, MCP tools/list contracts, and TypeScript types. The inspector reflects them in real time as you save.

tools/create-payment.ts typescript

import { defineTool, schema } from '@mcify/core';
import { requireAuth, rateLimit } from '@mcify/core/middleware';
import { z } from 'zod';

export const createPayment = defineTool({
  name: 'khipu_create_payment',
  description: 'Create a Khipu payment link',
  middlewares: [requireAuth(), rateLimit({ max: 60, windowMs: 60_000 })],
  input: z.object({
    subject: z.string().min(1).max(255),
    currency: z.enum(['CLP', 'USD']),
    amount: z.number().positive(),
  }),
  output: z.object({
    paymentId: z.string(),
    paymentUrl: schema.httpUrl(),
  }),
  handler: async (input, ctx) => {
    return ctx.fetch('https://payment-api.khipu.com/v3/payments', {
      method: 'POST',
      headers: { 'x-api-key': process.env.KHIPU_API_KEY },
      body: JSON.stringify(input),
    }).then((r) => r.json());
  },
});

Three steps

From zero to a deployable MCP server. AGENTS.md ships with the template, so any AI assistant follows the conventions automatically.

Scaffold

npx @mcify/cli@alpha init my-mcp
cd my-mcp
pnpm install

Generates the project, an AGENTS.md for your AI agent, and a mcify.config.ts with one example tool.

Develop with the inspector

pnpm dev
# → http://localhost:8888/mcp   (your server)
# → http://localhost:3001       (inspector)

Hot reload reflects your tool edits in the inspector instantly. Invoke from the Playground tab; see latency, args, and result live.

Ship

mcify deploy cloudflare        # Cloudflare Workers
mcify deploy vercel --prod     # Vercel Edge
mcify deploy docker --tag :latest --push

One command per target. Bundles, generates config, calls the right CLI under the hood. Fly.io and Railway ship next.

Reference connectors

Real APIs wired to mcify, shipped as both runnable examples and clonable templates. Used by Lelemon Agentes in production.

Khipu

live

Chilean payment links — sandbox-ready reference connector with two tools and a Zod-validated client.

mcify init my-server --template example-khipu Source on GitHub →

Bsale

planned

Chilean DTE / billing — emit invoices, list documents, look up clients.

Coming soon

Fintoc