Grade B
ai·rete·rag
com.ai-rete-rag/ai-rete-rag-mcp · v0.12.1 · 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
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Source: https://github.com/zaharajabeen13-create/ai-rete-rag-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 10 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_domain). Require confirmation before the agent calls them. |
What was checked
- https://ai-rete-rag.com/mcp: answers without auth
- https://ai-rete-rag.com/mcp/auth: requires auth
- pypi: ai-rete-rag-mcp@0.12.1 (static checks only; code not executed)
Public tools: decide, list_rules, get_parameters, ingest_text, list_documents, delete_domain, get_rule_source, put_rules, import_policy_rules, get_usage
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-ai-rete-rag-ai-rete-rag-mcp-e2a49d73)