Grade B
NoGPU
io.github.doronp/nogpu · v0.2.3 · score 81/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Free report: how many of your LLM's classification calls a small CPU model can answer alone.
Source: https://github.com/doronp/nogpu-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 4 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (nogpu_delete). Require confirmation before the agent calls them. |
| Medium | MW002 | Package https://github.com/doronp/nogpu-mcp/releases/download/v0.2.3/nogpu-mcp-0.2.3.mcpb is published without a fixed version. |
What was checked
- https://nogpu.dev/mcp: answers without auth
- mcpb: https://github.com/doronp/nogpu-mcp/releases/download/v0.2.3/nogpu-mcp-0.2.3.mcpb@? (static checks only; code not executed)
Public tools: nogpu_report, nogpu_status, nogpu_buy, nogpu_delete
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-doronp-nogpu-e5882adc)