What it does
RigBase publishes measured tokens-per-second figures for local LLMs running on home AI rigs. Its listing says it supports searching builds, checking whether a model can run on a given setup, and finding the best GPU, with data that is sourced and linked.
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
RigBase
Measured local-LLM tok/s on home AI rigs. Search builds, can-it-run, best GPU; sourced + linked.
v1.0.1As shown on registry.modelcontextprotocol.io when we last read it