What it does
The publisher describes the server as validating AI infrastructure code on real virtual machines, with no containers or sandboxes, and as correcting its own code until it runs. It is listed in the development category. No further documentation was available for this entry.
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
sh.antrieb/antrieb
Validates AI infra code on real VMs. Self-corrects until it works. No containers, no sandboxes.
v1.0.1As shown on registry.modelcontextprotocol.io when we last read it