org.aioq/aio
org.aioq/aio · v0.2.0 · score 89/100 · 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
AI integrity standards, benchmarks, and EU AI Act-aligned Tier 0 model certification
Source: https://github.com/AI-Integrity/aio-standards
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 22 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 3 tool(s) can execute commands or delete data (get_eval_items, start_eval_attempt, submit_eval). Require confirmation before the agent calls them. |
What was checked
- https://aioq.org/mcp: answers without auth
Public tools: list_papers, get_paper, get_benchmark_distribution, get_bench_items, submit_bench_run, get_framework_vocabulary, list_standards_packs, get_standards_pack, register_for_certification, get_eval_items, start_eval_attempt, submit_eval, verify_certification, list_rfcs, get_rfc, submit_rfc_comment, aio_lookup_reference, aio_lookup_org_priority, list_contribution_tasks, get_contribution_task, submit_contribution, get_contribution_status
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/org-aioq-aio-f6d05150)