Start with your AI
Deploy with Cursor
Connect Cursor to Atlas Cloud over MCP, approve your workspace, and deploy a web app with hosting, Postgres and file storage.
Deploy with Codex
Connect Codex to Atlas with remote HTTP MCP and OAuth, then deploy your local web application.
Deploy with Claude Code
Connect Claude Code to Atlas using HTTP MCP and browser authorization, then upload and deploy your project.
Build and operate
Deploy an AI-built app with Atlas Cloud
How to take an app built with Codex, Claude Code or Cursor live with Atlas: deployment fit, hosting, Postgres, storage and monthly INR billing.
From local source to a live app
The Atlas direct-source deployment workflow: source archive, application hosting, Postgres, file storage, safe retries, and live verification.
Add Postgres and file storage
Use Atlas-managed Postgres connections and the project-scoped Atlas file API from server-side application code.
Capabilities and limits
What Atlas MCP can do, its supported deployment workflow, access controls, source limits, and placement boundaries.
Understand pricing and usage
Atlas usage-based service charges, applicable tax, invoice totals, and honest handling of unavailable or delayed usage metrics.
Troubleshoot a deployment
Resolve Atlas connection, source upload, build, runtime, and usage issues using actual statuses and bounded logs.
The Atlas connection
Atlas exposes a remote MCP server with native OAuth authorization. Read the capabilities and limits before choosing it for a project.
https://mcp.atlasos.one/api/mcpThis is a client configuration URL. Start browser sign-in from your AI client's MCP setup. For a machine-readable overview, see llms.txt and Atlas MCP metadata.