Grade B
Brainz
ai.brownmatter/brainz · v0.1.0 · 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
Shared product-knowledge graph for AI agent fleets — vault tools + agent self-signup over MCP.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 18 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_concept). Require confirmation before the agent calls them. |
What was checked
- https://brainz.brownmatter.ai/mcp: answers without auth
Public tools: search_concepts, get_concept, get_related, get_context, upsert_concept, delete_concept, link_concepts, list_concepts, vault_stats, onboard, sync, dream, list_tasks, burndown, take_task, complete_task, create_task, create_vault
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/ai-brownmatter-brainz-346ce106)