What it does
StackBench is an MCP server that covers GPU and LLM inference benchmarks. According to its publisher, it also supplies hardware evidence, deployment recommendations and launch configs.
It falls under cloud and DevOps tooling, so it may be relevant to teams choosing hardware or settings for running LLM inference. The publisher's description does not list specific supported models, hardware, or workflows.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
ComputeSage StackBench
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
v0.2.1As shown on registry.modelcontextprotocol.io when we last read it