Grade D
dev.primitive/email
dev.primitive/email · v0.2.0 · score 57/100 · 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
Email infrastructure for AI agents — send, receive, search, and reply to email over MCP.
Source: https://github.com/primitivedotdev/primitive-mono-repo
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 14 tool(s) to anyone, no credentials needed. |
| Critical | MW101 | tool 'awaitReply': description contains instruction-like text aimed at the model ('Do not tell the user'). Possible tool poisoning. |
What was checked
- https://www.primitive.dev/mcp: answers without auth
Public tools: getAccount, getInboxStatus, getOutboundStatus, listEmails, searchEmails, getEmail, replyToEmail, sendEmail, listSentEmails, getSentEmail, awaitReply, getConversation, getEmailAttachment, createEmailAddress
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/dev-primitive-email-0240ec22)