Skip to main content
Exepad
For Agents

An agent can take an app all the way to a live address.

Most builders let an agent write code. Exepad lets an agent create the app, change it, publish it and watch it run — from one key you hand over once.

Create an app
curl -X POST https://api.exepad.com/v1/apps \
  -H "Authorization: Bearer $EXEPAD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Client intake",
    "type": "form",
    "description": "A client intake form with an admin dashboard"
  }'

Requires Pro and a funded balance · Published in minutes

See what changes ↓
THE BARRIER

What normally stops you

Most agent stories stop at generating code. Ours stops at a published, running app. An agent can scaffold a project in seconds and then stall: someone still has to install it, wire a database, connect a sign-in, put it on an address, and check whether any of it works. That last mile is the part no agent owns, so the human never actually leaves the loop.

What changes for you

Four things that work differently once you build this way.

01

The whole lifecycle, as tools

Before

Your agent hands back a folder of code. Everything after that — installing it, giving it a database, putting it somewhere people can reach — is a person at a terminal.

After

26 working tools cover the job end to end: create an app from a description, modify it, upload files, publish, unpublish, and read back logs, errors and health. The agent finishes what it started.

02

Ask before acting

Before

An agent editing an app it cannot see is guessing. It rewrites the page it was asked to extend, and you find out from the diff.

After

It reads the app's current configuration back first, then makes a change that fits what is already there. Look, then edit.

03

The agent builds; you hold the wallet

Before

Giving an agent a payment method is the reason most people never give one anything. The blast radius is your card, not your budget.

After

A key spends from the balance you funded and can do nothing else with your money. It cannot add to that balance and it cannot touch your payment method.

04

Plain REST too

Before

Every agent integration assumes one protocol, and half of what you run does not speak it. So whichever half of your fleet does not speak it is locked out.

After

The same lifecycle is a plain REST API on the same key. Agents that speak MCP call the tools; everything else posts JSON and gets the same result.

The same app, three ways

One app, three ways to build it: describe it yourself, write the components by hand, or hand over the key and read the logs afterwards. The lanes meet at the same published address.

The surfaces

One key, two ways to call it. Both surfaces run the same lifecycle against the same apps, so an agent can start on one and finish on the other.

  • REST

    https://api.exepad.com/v1

    Apps and their config, edits with streaming logs, files, publishing, domains, auth, observability and webhooks. A Bearer key on every request.

  • MCP

    https://mcp.exepad.com

    26 working tools over JSON-RPC for any agent that speaks the Model Context Protocol. The same operations, discovered rather than documented.

But what about…

What does an agent need before it can build anything?+

An active Pro subscription and a funded wallet balance, or auto-reload enabled. Usage is billed per operation from that balance. Mint a key in your account, give it to the agent, and it can create, edit and publish apps until the balance runs out.

Does every app my agent publishes become an MCP server?+

No, and we would rather say so plainly than let you find out mid-integration. MCP is how an agent builds apps on Exepad — it is not something a published app turns around and exposes. A live app has no MCP endpoint to call.

Can an agent spend money I have not already put there?+

No. A key spends from your balance and cannot add to it or touch your payment method. That is the whole boundary: the agent decides what to build, you decide how much there is to build with, and those two decisions stay on opposite sides of the key.

Can an agent undo a change it got wrong?+

Not on its own. There is no restore tool in the agent surface, so an agent cannot put an app back to an earlier version. Version history and restore live in Studio, where a person does it. Plan for a human on that step, because there is one.

What if my agent does not speak MCP?+

Use the REST API instead. It is the same key and the same lifecycle: create an app from a description, read its config, edit it, upload files, publish, unpublish, and pull logs, errors and health. Anything that can post JSON can build here.

How do I know what the agent actually did?+

Every edit streams its log while it runs, and you can pull logs, errors and health for an app afterwards over either surface. Webhooks push the same events to you. When you want to inspect the result yourself, the app is in Studio like any other.

Free covers simple web apps — three of them, one live at a time. The developer API is not part of it. An agent needs a key, and a key needs Pro.

Pro is $25/month and is what a key requires: unlimited full-stack apps, advanced AI models, and a balance the agent draws down per operation as it works.

See plans

Hand over the key. Get a running app.

One key, 26 tools, and an agent that finishes the job — from a sentence to a live address, without you in the loop.

Get an API key →