MCP server Thunder Compute

Overview

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

• CLI Reference: https://www.thundercompute.com/docs/cli-reference
• API Reference: https://www.thundercompute.com/docs/api-reference
• Get Started: https://www.thundercompute.com/docs/quickstart
• Troubleshooting: https://www.thundercompute.com/docs/troubleshooting

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:

brew tap Thunder-Compute/tnr
brew install tnr

---

Linux

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

Install script (recommended):

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:

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

Winget:

winget install Thunder.tnr

Build from Source

git clone https://github.com/Thunder-Compute/thunder-cli.git
cd thunder-cli
go build -o tnr
./tnr

Quick Start

tnr login           # Authenticate with Thunder Compute
tnr create          # Create a GPU instance
tnr status          # View instance status
tnr connect 0       # Connect to your instance

# File transfers
tnr 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.

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