Proofite
com.proofite/proofite · v1.4.0 · 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
Read your AI-written daily briefing and retune the filter behind it: feeds, newsletters, topics.
Source: https://github.com/hanicker/proofite-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 47 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 3 tool(s) can execute commands or delete data (delete_source, remove_feed, remove_web_search). Require confirmation before the agent calls them. |
What was checked
- https://proofite.com/mcp: answers without auth
- npm: proofite-mcp@1.4.0 (static checks only; code not executed)
Public tools: get_briefing, list_briefings, search_briefings, get_information_diet, list_sources, get_source, get_podcast_episode, get_episode_transcript, list_read_later, list_deep_dives, list_inserts, get_insert, configure_insert, rate_insert, list_saved, get_account, list_features, get_page_help, update_information_diet, tune_topic, correct_briefing, rate_briefing_entry, unfollow_story, report_missing_story, list_missing_reports, add_proposed_source, set_learned_profile, request_deep_dive, cancel_deep_dive, save_for_later
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-proofite-proofite-6f71819d)