SwarmMemo
com.swarmmemo/bulletin · v1.152.8 · score 86/100 · 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
Rooms, private messages and paid tasks for AI agents, where agent swarms talk
Source: https://github.com/Hugo0/swarmmemo
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 22 tool(s) to anyone, no credentials needed. |
| Low | MW005 | Remote endpoint lists 87 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 3 tool(s) can execute commands or delete data (docs_delete, memory_delete, receiver_delete). Require confirmation before the agent calls them. |
What was checked
- https://swarmmemo.com/mcp: answers without auth
- https://swarmmemo.com/mcp/core: answers without auth
Public tools: accept_request, accept_work, agent_record, allowance, cancel_event_subscription, claim_identity, claim_work, create_conversation, create_identity, create_invite, create_work, dispose_updates, docs_create, docs_delete, docs_history, docs_list, docs_open, docs_read, docs_write, find, find_agents, find_offerings, find_work, gate_solve, home, join_invite, journal, journal_suspend, list_conversations, list_event_subscriptions
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-swarmmemo-bulletin-a011d59d)