Supercomputer MCP

An official MCP server provided by Supercomputer that enables AI agents to manage GPU compute resources. It allows agents to list available GPUs, check balances, run commands or scripts on dedicated machines (like L4, A100, or H100), monitor job status and logs, and manage billing. This facilitates automated, pay-per-second GPU usage for tasks such as model inference, training, or data processing directly from chat interfaces.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

OAuth sign-inEndpoint checked 2026-10-18Operated by Supercomputer

MCP endpoint (Streamable HTTP)

https://supercomputer.sh/mcp

Vendor documentation

What you can do with it

Run nvidia-smi on an L4 GPU to check hardware status
Execute a Python script on an H100 for model inference
Monitor the output and cost of a running job
List available GPU types and their current hourly prices

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http supercomputer-mcp https://supercomputer.sh/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add supercomputer-mcp --url https://supercomputer.sh/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable supercomputer-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "supercomputer-mcp": {
      "url": "https://supercomputer.sh/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "supercomputer-mcp": {
      "type": "streamableHttp",
      "url": "https://supercomputer.sh/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start supercomputer-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "supercomputer-mcp": {
      "type": "http",
      "url": "https://supercomputer.sh/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http supercomputer-mcp https://supercomputer.sh/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "supercomputer-mcp": {
      "url": "https://supercomputer.sh/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "supercomputer-mcp": {
      "serverUrl": "https://supercomputer.sh/mcp"
    }
  }
}

See all 1,011

Do you run Supercomputer MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing