Grade B
RogerThat
io.github.opcastil11/rogerthat · v1.25.0 · 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
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Source: https://github.com/opcastil11/rogerthat
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 19 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (secret_drop_recipe). Require confirmation before the agent calls them. |
What was checked
- https://rogerthat.chat/mcp: answers without auth
- npm: rogerthat@1.25.0 (static checks only; code not executed)
Public tools: open_remote_control, open_video_call, make_remote_link, update_channel_ttl, create_channel, join, send, listen, wait, roster, history, leave, create_account, create_identity, send_dm, read_inbox, wait_dm, set_avatar, secret_drop_recipe
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-opcastil11-rogerthat-4e238d52)