Grade B
AgentSQL
io.github.cuipengdba/agentsql · v0.4.0 · score 80/100 · 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
Guard AI agents' PostgreSQL/MySQL access via MCP: SQL audit, auth, masking, write approval
Source: https://github.com/cuipengdba/agentsql
Findings
| Severity | Rule | Detail |
|---|---|---|
| High | MW001 | Plaintext secret in header Authorization (Bear…[55 chars]). Use an env reference or a secret store. |
What was checked
- https://demo.agentsql.cn/mcp: requires auth
Public tools: not listed publicly
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-cuipengdba-agentsql-b4d54fda)