Hi team 👋
I ran a free deep security scan of modelcontextprotocol/servers 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: 53/100 · Grade D
| Severity |
Count |
| 🔴 Critical |
0 |
| 🟠 High |
11 |
| 🟡 Medium |
88 |
| 🟢 Low |
4 |
Summary: 11 high + 88 medium + 4 low findings across the official reference server implementations — affects the entire MCP ecosystem
📋 Full report with findings and evidence: https://mcpsafe.io/registry/github/modelcontextprotocol/servers
Add a security badge to your README
[](https://mcpsafe.io/registry/github/modelcontextprotocol/servers)
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 modelcontextprotocol/servers 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: 53/100 · Grade D
Summary: 11 high + 88 medium + 4 low findings across the official reference server implementations — affects the entire MCP ecosystem
📋 Full report with findings and evidence: https://mcpsafe.io/registry/github/modelcontextprotocol/servers
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