Bento
io.github.dzhng/bento · v1.0.0 · 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
One subscription for every kind of AI: images, video, voice and more.
Source: https://github.com/dzhng/bento-releases
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 214 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 23 tool(s) can execute commands or delete data (agent_delete, user_machine_delete, sync_machine_delete, app_domain_delete, app_delete and 18 more). Require confirmation before the agent calls them. |
What was checked
- https://mcp.bento.ing/: answers without auth
Public tools: recording_operation_create, skill_list, agent_list, agent_roster_list, agent_create, agent_default_update, agent_update, session_agent_update, app_agent_update, agent_delete, device_approve, whoami, user_profile_get, user_profile_update, user_api_key_list, user_api_key_create, user_api_key_revoke, user_machine_create, user_machine_list, user_machine_delete, user_invitation_list, user_invitation_accept, feedback_create, sync_machine_create, sync_machine_list, sync_machine_delete, app_credential_list, app_credential_create, app_credential_revoke, app_domain_list
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-dzhng-bento-6b880ce1)