Ways to use Superjolt

MCP is the tools your agent calls; the API is for CI/scripts; the dashboard is read-mostly. All point at the same control plane.

Superjolt is one control plane with a few front doors. They all act on the same VMs, domains, and account — pick whichever fits the moment.

MCP — the tools (start here)

The Superjolt MCP server (https://mcp.superjolt.com) is where the tools live — create_vm, add_domain, open_port, and the rest. Any MCP-capable agent (Claude Code, Cursor, Claude Desktop, …) connects to it and calls them directly. This is the primary way an agent operates Superjolt.

Getting connected is three steps:

  1. Add Superjolt MCP at mcp.superjolt.com — tell your agent, or follow the per-client setup guides.
  2. Sign in when your agent prompts you.
  3. Say “hello superjolt” — your agent spins up a live demo VM you can edit on the spot.

Getting started · MCP tools reference

API — for CI and scripts

Everything the agent does is a REST call under the hood. For automation without an agent — a deploy step, a cron job — hit https://api.superjolt.com/v1/* directly with an API token (Authorization: Bearer sj_live_…). Mint a token from the dashboard.

Dashboard — read-mostly

The dashboard is where you watch what’s running, see costs, and mint API tokens. It’s deliberately read-mostly — provisioning and changes happen through the agent (MCP), not by clicking around.

What’s next