Superserve Sandbox MCP
Secure virtual machines for agents hosted by Superserve
Ads
Overview
> Create, run, and manage Superserve sandboxes from any MCP client. The Superserve MCP server (@superserve/mcp) exposes sandbox primitives as Model Context Protocol tools, so any MCP-capable client — Claude, Cursor, VS Code, Windsurf, Codex — can create sandboxes, run commands, read and write files, build templates, broker secrets, and control network access in an isolated Firecracker microVM. Run it two ways: locally over stdio via npx, or against the hosted endpoint at https://mcp.superserve.ai with no local install. Both authenticate with your SUPERSERVE_API_KEY and target a sandbox per call by ID. It's a thin wrapper over the TypeScript SDK, so the per-sandbox data-plane token never reaches the model.
Installation
https://mcp.superserve.ai
Configuration
{
"mcpServers": {
"superserve": {
"command": "npx",
"args": ["-y", "@superserve/mcp"],
"env": { "SUPERSERVE_API_KEY": "ss_live_xxxxxxxxxxxxxxxx" }
}Capabilities
- Create and run sandboxes
Ask your assistant to spin up an isolated Firecracker microVM with `sandbox_create`, then execute commands inside it via `sandbox_exec` and get stdout, stderr, and exit codes.
- Manage files in sandboxes
Have your AI read, write, or list files with `sandbox_files_read`, `sandbox_files_write`, and `sandbox_files_list`, or download an entire directory as a ZIP using `sandbox_files_download_dir`.
- Control sandbox lifecycle
Pause a sandbox to preserve its state with `sandbox_pause`, resume it with `sandbox_resume`, or permanently delete it using `sandbox_kill` when you're done.
- Publish preview URLs
Ask your assistant to expose a running service by calling `sandbox_preview_url` to get a clean public URL or an expiring private signed link for a specific port.
- Manage secrets and templates
List available team secrets with `secret_list`, bind them to sandboxes via `sandbox_attach_secret`, or create custom base images with `sandbox_template_create` for specific CPU/memory/disk shapes.
Tags
- cloud-infrastructure
- development
- devops
Related MCP servers
Context7 MCP
OfficialOfficial Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.
Chrome DevTools MCP
OfficialOfficial Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.
Mastra/mcp
OfficialClient implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
GitHub MCP Server
OfficialConnect your AI assistant to GitHub repositories, issues, pull requests, and search.