Thunder Compute

io.github.Thunder-ComputePublished by GitHub account Thunder-Computev1.0.0Updated Oct 25, 2026

GPU cloud platform — create, manage, and monitor instances, snapshots, SSH keys, and billing.

VerifiedStreamable HTTPWeb executableCloud & InfrastructureAI & ML

Overview

AI-generated overview

Remote MCP endpoint for Thunder Compute that lets an assistant create, manage and monitor cloud GPU instances, snapshots, SSH keys and billing.

What you can do
  • Create, configure and delete cloud GPU instances, and check their status
  • Manage snapshots and SSH keys for secure access to instances
  • Monitor account usage and billing
  • Work with instance specifications and compute resources for AI/ML prototyping
When to use it
Useful when you want an assistant to spin up or tear down GPU machines for AI/ML experimentation, or to check instance status and billing without leaving the chat. It fits teams already using Thunder Compute as their GPU cloud.
Requirements
A remote endpoint at api.thundercompute.com over streamable HTTP; OAuth authentication is required, so a Thunder Compute account is needed. No environment variables or headers are declared.
Before you install
The server can create and delete GPU instances and manage SSH keys, which changes infrastructure and can incur charges on your Thunder Compute account. Review any create or delete action before approving it, and check billing impact.

Installation

In SourceWeft

  1. Open Thunder Compute in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. 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/io.github.Thunder-Compute%2Fthunder-compute/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.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "thunder-compute": {
      "type": "http",
      "url": "https://api.thundercompute.com:8443/mcp"
    }
  }
}

README

Overview

[License: MIT] [Go Version] [Release] [macOS] [Linux] [Windows]

tnr is the official command-line interface for Thunder Compute, a high-performance cloud GPU platform built for AI/ML prototyping and experimentation. Using a proprietary orchestration engine, Thunder Compute delivers fast provisioning, low-latency execution, and low-cost GPU compute designed for developer workflows.

The tnr CLI supports:

  • Provisioning and managing GPU instances
  • Configuring compute resources and instance specifications
  • Secure SSH access and session management
  • File transfer capabilities (SCP upload and download)
  • Port forwarding for accessing remote services locally
  • Automated update checks and version management
  • Cross-platform support for macOS, Linux, and Windows

Documentation

Installation

Install tnr using one of the supported methods below. You may also download installers and binaries directly from the Latest Release page.

macOS

Download the .pkg installer for your platform from the Latest Release page (tnr_*_darwin_arm64.pkg for Apple Silicon, tnr_*_darwin_amd64.pkg for Intel).

Homebrew:

bash
brew tap Thunder-Compute/tnrbrew install tnr

Linux

Download .tar.gz, .deb, .rpm, or .apk packages from the Latest Release page.

Install script (recommended):

bash
curl -fsSL https://raw.githubusercontent.com/Thunder-Compute/thunder-cli/main/scripts/install.sh | bash

Windows

Download the .msi installer for your platform from the Latest Release page.

Scoop:

powershell
scoop bucket add tnr https://github.com/Thunder-Compute/scoop-bucketscoop install tnr

Winget:

powershell
winget install Thunder.tnr

Build from Source

bash
git clone https://github.com/Thunder-Compute/thunder-cli.gitcd thunder-cligo build -o tnr./tnr

Quick Start

bash
tnr login           # Authenticate with Thunder Computetnr create          # Create a GPU instancetnr status          # View instance statustnr connect 0       # Connect to your instance
# File transferstnr scp myfile.py 0:/home/ubuntu/tnr scp 0:/home/ubuntu/results.txt ./
tnr delete 0        # Delete instance

tnr login opens a browser and returns to a loopback callback on 127.0.0.1. On a headless or remote machine where that callback cannot be reached, create a named API token in Console Settings and run tnr login --token <named_api_token> instead.

Bug reports and feedback

Run tnr report for a guided report in the style of tnr create: choose Report a problem or Suggest an improvement, write a one-sentence summary and the details, then review the report and choose Send report, Edit report, or Cancel. Sign in before starting. --kind, --subject, and --details or --details-file fill in their steps, which are then skipped, and supplied text is sent as given. Quitting sends nothing and exits with code 130. Noninteractive reports default to bugs; use --kind feedback for product feedback.

sh
tnr report --subject "Upload connection drops" --details-file ./report.txt --component cli --instance 42tnr report --kind feedback --subject "Show remaining disk space" --details "Please show disk usage in the instance list." --yes --jsontnr report --subject "Unexpected result" --details-file - --dry-run --json < ./report.txt

Noninteractive submission requires --subject, --details or --details-file, and --yes. --json never prompts. --details-file - reads standard input. --details and --details-file are mutually exclusive. Subject and details limits are 200 and 10,000 Unicode characters; oversized text is rejected instead of truncated. --dry-run previews without authentication or submission and identifies the missing server-resolved requester.

Optional context flags are --component (cli, console, api, mcp, virtualization, or unknown), either --instance or --sandbox, and --occurred-at (RFC 3339). The report includes the CLI version, build commit and date, OS, and architecture. The server records submission time and resolves the requester from your login or verified API token owner. No logs, environment variables, shell history, or workload files are collected automatically. Only include evidence you intend to share with support, and omit credentials.

Successful submissions print an opaque report reference. Exit zero means a successful submission or dry run. Any failure exits nonzero and retains the entered report in the error output, so you can submit it again. JSON errors include error, message, and report. Reporting skips automatic update and subscription checks.

License

This project is licensed under the MIT License. See LICENSE for details.

Source: README.md at commit 4d65c68

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

85% 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
  • License10 pts