Skip to content
mcp/skillhub

Liquid Compute GPU test MCP Server

by liquid-computecom.liquidcompute/gcatv1.0.1

Run GPU acceptance tests on your NVIDIA GPU nodes over SSH: DCGM, GEMM, HBM/PCIe bandwidth, NCCL.

0remoteofficial registry

context tax

needs auth

security

97/100

cold start

hosted

freshness

Active3d ago

Our reading of Liquid Compute GPU test, from the data

Liquid Compute GPU test is an MCP server from liquid-compute, listed in the official MCP Registry.

Its endpoint requires sign-in or an API key just to list tools, so we haven't measured its token cost; we never use real credentials.

Maintenance is active: the last public signal was 3 days ago (2026-10-15).

It runs as a hosted endpoint, so there is nothing to install.

Install Liquid Compute GPU test MCP server

Install in Claude Code

claude mcp add --transport http gcat https://api.liquidcompute.co/mcp

Remote endpoints

  • streamable-httphttps://api.liquidcompute.co/mcp

Security signals

97/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.

Deductions

  • No security policy (SECURITY.md)-3

Checks

  • ✓Repository hygiene (archived, activity, license, security policy)
  • ○Package metadata (install scripts, provenance) — pending
  • ○Tool descriptions (prompt-injection and hidden-text heuristics) — pending
  • ○Source scan (secrets, CVEs, risky code) by vectra-guard — pending

Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules

Freshness

Active — last maintenance signal 3d ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-10-15 · 3d ago · GitHub

  2. Latest release

    2026-10-15 · 3d ago · GitHub · v1.0.1

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-10-15 · 3d ago · official registry · v1.0.1

FAQ

›How do I install the Liquid Compute GPU test MCP server in Claude Code?

Run: claude mcp add --transport http gcat https://api.liquidcompute.co/mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Liquid Compute GPU test require an API key?

No required environment variables are declared in its published metadata.

›Can I use Liquid Compute GPU test as a remote (hosted) MCP server?

Yes. It is a hosted MCP server; connect to its URL with any client that supports remote MCP.

›Is Liquid Compute GPU test in the official MCP registry?

Yes, as com.liquidcompute/gcat.

Sources and method

Official MCP Registry entry
updated 2026-10-15
GitHub repository
fetched 2026-10-19
Last checked against all sources
2026-10-19

The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.