Liquid Compute GPU test — Claude Code MCP server: GPU tests
This MCP server runs acceptance tests on NVIDIA GPU nodes and returns a report for the selected profile. Use it to check hardware before putting it to work.
claude mcp add --transport http gcat https://api.liquidcompute.co/mcpWhat Liquid Compute GPU test does
The agent selects a profile for your nodes, helps arrange SSH access, and starts the test after a connection check. The report includes NVIDIA diagnostics and measurements of compute performance, memory bandwidth, and networking; results are compared with the profile thresholds. Profiles cover A10, H100, H200, B200, and B300 nodes, plus two- or four-node clusters using RDMA.
You need a Liquid Compute account and nodes running Ubuntu 22.04 or 24.04, NVIDIA driver 580 or later, and CUDA 13.0 or later. The nodes must accept SSH from the service's addresses, and the user needs root or passwordless sudo. Keep every GPU idle during the test. It puts the GPUs under full load and may run for 90 minutes or longer, so occupied GPUs rule out a safe run.
The agent must get your separate approval before adding nodes and starting a test; turn off automatic approval for these actions. Temporary test files are removed afterwards, but SSH access remains until you delete the line from authorized_keys. The report describes measurements from the test window; it is neither certification nor a warranty.
What it helps with
- check an NVIDIA GPU node against a hardware profile
- compare node measurements with profile thresholds
- verify SSH connectivity before loading the GPUs
- review hardware measurements from a test run
Example prompts for the agent
- Run an acceptance test on my NVIDIA GPU nodes and select a suitable profile.
- Check SSH access to the nodes, then wait for my approval before starting the test.
- Show me the test results and prepare a report link.
How to install Liquid Compute GPU test
Platform CLI: remote server
claude mcp add --transport http gcat https://api.liquidcompute.co/mcpPlatform CLI: remote server
codex mcp add liquid-compute-gpu-test --url https://api.liquidcompute.co/mcpConfig file
{
"mcpServers": {
"liquid-compute-gpu-test": {
"url": "https://api.liquidcompute.co/mcp"
}
}
}Config file
{
"servers": {
"liquid-compute-gpu-test": {
"type": "http",
"url": "https://api.liquidcompute.co/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http liquid-compute-gpu-test https://api.liquidcompute.co/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Liquid Compute GPU test
How do I install Liquid Compute GPU test in Claude Code?
Run claude mcp add --transport http gcat https://api.liquidcompute.co/mcp, then sign in when the agent connects for the first time.
What does Liquid Compute GPU test do?
It tests NVIDIA GPU nodes using a selected profile and reports measurements alongside the profile thresholds.
What do I need to run a test?
You need a Liquid Compute account, a supported Ubuntu and NVIDIA driver version, SSH access from the service's addresses, and a user with root or passwordless sudo. Keep the GPUs idle for the full test.
