For developers (technical)

Your APIs in your coding tools, and jobs on your own machines

Use your company's APIs from Claude Code, Cursor or any MCP client, and let assistants run jobs on machines you control.

Start free Step-by-step guide

A gateway with its access key and the ready-made command for adding it to a coding assistant.

Who it is for

Developers and platform teams. This is the technical path: the other use cases do not need any of it.

What it does, in one story

Your internal systems, inside the tools you code with

You connect your orders API once and publish it on a gateway. The gateway page gives you a ready-made command for Claude Code, Cursor or Claude Desktop. Now you ask "What is the status of order NW-10428?" in your editor, and it calls your API.

Then you start a runner on your build server. An assistant that needs a Linux machine sends its work there: build a branch, run the tests, collect a log, and report back. You decide who may use the runner, and what it may and may not run.

What the assistant does

Turns an OpenAPI, GraphQL, SOAP or gRPC description, or an npm package, into tools
Serves them to coding assistants over MCP, or as Agent Skills or UTCP
Runs jobs on any machine you control, matched by labels like os=linux
Answers on an OpenAI-compatible API, and from a command line tool

What you need

An API connected in almyty
A coding assistant that speaks MCP, such as Claude Code or Cursor
For a runner: a machine with Node.js where you can install a package

How to set it up

1
Publish your API's tools
Create an MCP gateway for the API. Copy its key and the ready-made setup.
2
Add it to your coding tool
For Claude Code it is one command. Every call shows up in Analytics.
3
Start a runner
Three commands on the machine, then let an agent send work there by label.

The full guide walks through every click, with pictures, in the docs.

Open the step-by-step guide