supercomputer
sh.supercomputerPublished by supercomputer.shOfficial publisherv0.4.4Updated Oct 24, 2026
GPU compute for agents: run commands on an L4/A100/H100, watch logs, billed per second.
Overview
Lets an assistant run commands on remote GPU machines (L4, A100, H100) and watch the logs, billed per second.
- What you can do
- This remote MCP server gives an assistant access to GPU compute: it can run commands on remote machines equipped with L4, A100 or H100 GPUs and follow the resulting logs. The registry description frames it as GPU compute for agents, with usage billed per second. No individual tools are listed in the supplied material, so the exact command and log operations are not documented here.
- When to use it
- Worth adding when an assistant needs to execute work that requires a real GPU — for example training, inference or other compute-heavy jobs — without the user provisioning and managing a machine. It is less relevant if the task only needs CPU-level work or an existing local environment.
- Requirements
- A remote streamable HTTP endpoint at supercomputer.sh; nothing is installed locally. The manifest declares no authentication, environment variables or headers, but the provider's documentation should be checked for any account, credential or access setup before use.
Installation
In SourceWeft
- Open supercomputer in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/sh.supercomputer%2Fsupercomputer/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"supercomputer": {
"type": "http",
"url": "https://supercomputer.sh/mcp"
}
}
}Tools
0Version history
1- v0.4.4LatestOct 15, 2026
Score
67% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.