Grade B
Mind Polling
com.mindpolling/mindpolling · v1.0.0 · 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
Polls of AI models: read public results with no key; create and run your own with an API key.
Source: https://github.com/news-community/mind-polling-public
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 22 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_webhook). Require confirmation before the agent calls them. |
What was checked
- https://mindpolling.com/mcp: answers without auth
- npm: mindpolling@1.0.0 (static checks only; code not executed)
Public tools: get_me, list_polls, get_poll, get_results, list_runs, list_calls, list_models, search_places, get_place, rotate_key, revoke_key, create_poll, update_poll, estimate_poll, start_poll, run_poll_now, pause_poll, get_live_run, list_changes, create_webhook, list_webhooks, delete_webhook
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-mindpolling-mindpolling-cdfca58d)