mcp

MCP serverDev tools

This app gives your AI access to Superserve sandboxes, small isolated machines it can use as its own workspace. Once added, your AI can create Firecracker microVMs, run commands inside them, and manage them while work is under way. It is useful whenever a task needs its own clean environment.

Available today. Use it from your connected AI after setup.

Add the app, then ask your AI to create a sandbox when a task needs its own environment. From there, you can ask it to run commands inside and manage the sandbox for you.

Then ask your AI: use mcp

What your AI can do with it

  • Create new Firecracker microVM sandboxes on demand
  • Run commands inside a sandbox
  • Manage sandboxes while a task is in progress
  • Keep work isolated from your own files and setup

From the project's README

As published by superserve-ai/superserve in README.md.

Getting Started

Visit superserve.ai or jump straight into the docs.

Structure

apps/
  console/                 # Sandbox dashboard (Next.js 16, App Router)
  ui-docs/                 # UI component docs (Vite)
packages/
  cli/                     # TypeScript CLI (@superserve/cli)
  python-sdk/              # Python SDK (superserve on PyPI)
  sdk/                     # TypeScript SDK (@superserve/sdk)
  ui/                      # Shared UI components (@superserve/ui)
  typescript-config/       # Shared tsconfig presets
  tailwind-config/         # Shared Tailwind config
docs/                      # Mintlify documentation site
tests/                     # SDK end-to-end tests

Monorepo managed with Bun workspaces, Turborepo, and uv workspaces.

Setup

bun install               # install all JS/TS dependencies
uv sync                   # install all Python dependencies

Development

bun run dev               # start all dev servers
bun run build             # build all packages
bun run lint              # lint all packages
bun run format            # format all files
bun run typecheck         # type check all packages
bun run test              # unit/integration tests

For more (per-package targets, dependency management, etc.), see CONTRIBUTING.md.

SDKs

Full reference at docs.superserve.ai.

Testing

bun run test                                        # unit tests (no credentials)
SUPERSERVE_API_KEY=ss_live_... bun run test:e2e     # e2e against staging

For environment overrides and single-language runs, see CONTRIBUTING.md.

Releasing

See RELEASING.md for publishing the SDKs to npm and PyPI.

Contributing

Contributions welcome — see CONTRIBUTING.md for guidelines.

License

Apache License 2.0 — see LICENSE.

Where to find us

Signals

GitHub stars
460
Forks
53
Last commit
Sep 2026
Advanced
Delivery
mcp MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
io-github-superserve-ai-mcp
Source
github.com/superserve-ai/superserve
Hosted endpoint
https://mcp.superserve.ai