Zambo
dev.zambo/zambo · v4.1.4 · 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
The verifiable work layer for AI: 153 tools, cross-AI handover, a verifiable receipt for every job.
Source: https://github.com/zambodotdev/zambo-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 37 tool(s) to anyone, no credentials needed. |
| Critical | MW101 | tool 'prompt_shield': description contains instruction-like text aimed at the model ('Ignore previous instructions'). Possible tool poisoning. |
What was checked
- https://zambo.dev/mcp: answers without auth
Public tools: capability_search, memory_recall, memory_remember, scam_check, day_pass_redeem, spend_limit_set, spend_limit_status, handover_accept, handover, handover_status, handover_list, zambo_home, activity_today, workflow_close, workflow_seal, zambo_universal, new_session, continuity_get_recent, continuity_list_threads, continuity_open_thread, continuity_start_thread, continuity_set_prefs, journal_log, live_price, pdf_extract, doc_intel, leadsignal, provibe_audit, ghost_audit_site, ghost_audit_status
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/dev-zambo-zambo-564f7264)