Vastai MCP Server

1. **Install uv** (Python package manager): ```bash brew install uv ```

Local serverstdioPython

What is the Vastai MCP MCP server?

  1. Install uv (Python package manager): bash brew install uv . That is what the vastai mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The tools it exposes

The server publishes 3 tools. What each one is for:

  • Prerequisites — 1. Install uv (Python package manager): bash brew install uv
  • Configuration — 1. Get your Vast.ai API key: - Log in to console.vast.ai - Go to Account > API Keys - Create or copy your API key
  • Troubleshooting — The Troubleshooting tool exposed by this server

What it needs from you

Configuration is passed through the environment: VAST_API_KEY, SSH_KEY_FILE, SSH_KEY_PUBLIC_FILE, JUPYTER_ENABLE_LAB. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  1. Install uv (Python package manager):

Getting it running

wandb on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Vastai MCP's toolset — Prerequisites, Configuration, Troubleshooting — is a fair guide to whether it matches your workflow. It is maintained by CryDevOk; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Prerequisites1. **Install uv** (Python package manager): bash brew install uv
Configuration1. **Get your Vast.ai API key**: - Log in to [console.vast.ai](https://console.vast.ai) - Go to Account > API Keys - Create or copy your API key
TroubleshootingThe Troubleshooting tool exposed by this server.

How to install the Vastai MCP MCP server

{
  "mcpServers": {
    "vastai": {
      "command": "uvx",
      "args": ["wandb"],
      "env": {
        "VAST_API_KEY": "your-value",
        "SSH_KEY_FILE": "your-value",
        "SSH_KEY_PUBLIC_FILE": "your-value",
        "JUPYTER_ENABLE_LAB": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  1. Install uv (Python package manager):
VariableDescriptionRequired
VAST_API_KEYCredential the server authenticates with.Yes
SSH_KEY_FILECredential the server authenticates with.Yes
SSH_KEY_PUBLIC_FILECredential the server authenticates with.Yes
JUPYTER_ENABLE_LABConfiguration value read at startup.Optional

Example prompts to try

  • Use Vastai MCP to Prerequisites.
  • Use Vastai MCP to Configuration.
  • Use Vastai MCP to Troubleshooting.

Frequently asked questions

It connects Vastai MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (Prerequisites, Configuration, Troubleshooting) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Vastai MCP directly.