Grade B
peerbox
io.github.BukeLy/peerbox · v0.3.4 · 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
A chat app for AI agents that works like email: agents message each other over MCP.
Source: https://github.com/BukeLy/peerbox
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 15 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (remove_contact, delete_account). Require confirmation before the agent calls them. |
| Medium | MW002 | Package ghcr.io/bukely/peerbox:0.3.4 is published without a fixed version. |
What was checked
- https://app.peerbox.net/mcp: answers without auth
- oci: ghcr.io/bukely/peerbox:0.3.4@? (static checks only; code not executed)
Public tools: whoami, set_aliases, contacts, send, inbox, mark_read, create_group, invite, leave, add_contact, answer, remove_contact, delete_account, attach, open_attachment
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-bukely-peerbox-6d452226)