Hi team 👋
I ran a free deep security scan of MiniMax-AI/MiniMax-MCP using MCPSafe — a purpose-built scanner for MCP servers using a 5-LLM consensus panel to detect prompt injection risks, over-scoped tool schemas, supply chain issues, and more.
Results: 91/100 · Grade B
| Severity |
Count |
| 🔴 Critical |
0 |
| 🟠 High |
0 |
| 🟡 Medium |
6 |
| 🟢 Low |
0 |
Summary: 6 medium-severity findings around MiniMax API tool schemas and AI model access permissions. No critical or high findings.
📋 Full report with findings and evidence: https://mcpsafe.io/registry/github/MiniMax-AI/MiniMax-MCP
Add a security badge to your README
[](https://mcpsafe.io/registry/github/MiniMax-AI/MiniMax-MCP)
This badge auto-updates whenever a new scan runs — great for showing users and enterprise customers your security posture at a glance.
Feel free to close this if you're already tracking these findings. Happy to answer any questions about specific findings.
— Truong BUI · mcpsafe.io
Hi team 👋
I ran a free deep security scan of MiniMax-AI/MiniMax-MCP using MCPSafe — a purpose-built scanner for MCP servers using a 5-LLM consensus panel to detect prompt injection risks, over-scoped tool schemas, supply chain issues, and more.
Results: 91/100 · Grade B
Summary: 6 medium-severity findings around MiniMax API tool schemas and AI model access permissions. No critical or high findings.
📋 Full report with findings and evidence: https://mcpsafe.io/registry/github/MiniMax-AI/MiniMax-MCP
Add a security badge to your README
This badge auto-updates whenever a new scan runs — great for showing users and enterprise customers your security posture at a glance.
Feel free to close this if you're already tracking these findings. Happy to answer any questions about specific findings.
— Truong BUI · mcpsafe.io