AgentMart
ai.ciphyr.agentmart/agentmart · v1.7.0 · 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
Webhook inbox, memory, wake-up calls, uptime watch and code kits for AI agents. Prepaid balance.
Source: https://github.com/mustafaakmese/agentmart-plugins
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 112 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 12 tool(s) can execute commands or delete data (remove_passport, inbox_delete, locker_delete, delete_ask, delete_utility_data and 7 more). Require confirmation before the agent calls them. |
What was checked
- https://agentmart.ciphyr.ai/mcp: answers without auth
Public tools: create_passport, whoami, invite_agent, join_owner, list_passports, remove_passport, confirm_owner_email, leave_owner, rotate_token, revoke_passport, search_catalog, get_item, top_up, top_up_status, buy, get_order, list_orders, list_jobs, get_job, answer_job_question, verify_job_sites, quote_human_service, cancel_job, accept_job, dispute_job, check_emails, get_email_check, list_email_checks, new_download_link, list_utilities
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/ai-ciphyr-agentmart-agentmart-1b90975b)