Skip to content
mcpfy
Start deploying

vibe

Describe it. Watch it scaffold.

Say what your MCP app should do in plain language and watch the server, the tool schemas and the interactive views build themselves, then take the code and keep going.

Start vibecodingSee an example

Our open source tools are used by developers at top companies

NorthwindApertureCogentLumenBrightpathSundialMeridianIroncladBlue HarborKestrel

How it runs

From a sentence to a deployed server

  1. 1

    Describe

    Say what the app should do.

  2. 2

    Scaffold

    Tools, schemas and views generated.

  3. 3

    Preview

    Try it in the Inspector instantly.

  4. 4

    Deploy

    Ship it from the same screen.

Real code, not a black box

Everything it generates is ordinary SDK code in your repository. Read it, edit it, or throw it away.

acme-mcp · zsh

➜ npx create-mcpfy-app

✓ tools/chart-sales.ts

✓ widgets/Chart.tsx

✓ mcpfy.config.ts

➜ mcpfy dev

ready on :4141 · 6 tools registered

tools/chart-sales.ts

export const chartSales = tool({
  name: "chart_sales",
  input: z.object({ period: z.string() }),
});

Views included

Interactive widgets are scaffolded alongside the tools that feed them, wired up and ready to render.

Cloud Inspectorsession #4f2a

San Francisco, CA

72°F

Partly cloudy · H 74° L 58°

now72°
2pm74°
3pm73°
4pm70°
5pm66°
6pm63°

→ tools/call

{
  "name": "display_weather",
  "arguments": { "city": "San Francisco" }
}

← result20041ms

{ "content": [{ "type": "resource" }] }

GPT-5.2

18/18

Claude

18/18

Gemini

17/18

Deploy from the prompt

The same session that generated the server can ship it to a live endpoint.

Deploymentsauto · on push
  • mainProduction12s
  • feat/chartsPreview9s
  • fix/authPreview11s

➜ npx mcpfy deploy

✓ live → my-server.mcpfy.ai/mcp

In the box

What it can build

1

Data tools

Query a database behind a typed schema.

2

API wrappers

Wrap an existing service as MCP tools.

3

Chart widgets

Interactive views rendered inline.

4

Workflows

Multi-step tools an agent can chain.

Build your first MCP app by describing it

Start deployingBook a call

Explore the rest of the platform

MCP Hosting

GitHub-native builds, preview URLs per branch, production endpoints with TLS and custom domains, and instant rollback, purpose-built for MCP traffic and the clients that connect to it.

Learn more

Cross-client testing

Your server behaves differently in ChatGPT than it does in Claude or Cursor.

Learn more

Publishing checks

Six categories of checks mapped to marketplace requirements, each failure with fix guidance and an autofix flow, plus live end-to-end runs inside the real clients.

Learn more

Cloud Inspector

Fire tool calls at your deployed server, read raw JSON-RPC frames, browse resources and preview widgets, against real clients, with no local setup.

Learn more

Public chat

Every deployment gets a shareable chat surface you can embed anywhere you already have an audience: no client install, no configuration.

Learn more

Analytics

Tool calls, sessions, error rates and latency percentiles broken down by client, client version, protocol version and country, with discovery traffic excluded by default.

Learn more

Everything on mcpfy Cloud shares one pipeline.