What it does
The server gives an agent access to a live catalogue of cloud GPUs. From there, the agent can deploy a GPU, stop it, or destroy it. The publisher describes billing as per second.
It is relevant to development and cloud operations workflows where an agent needs to provision GPU capacity and release it again. The publisher's description does not give further detail on supported providers, GPU types 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
io.github.jyswee/computegpu
Rent cloud GPUs from your agent: live catalogue, deploy, stop, destroy. Per-second billing.
v1.2.1As shown on registry.modelcontextprotocol.io when we last read it