Hi team 👋
I ran a free deep security scan of the @modelcontextprotocol/server-filesystem npm package 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: 68/100 · Grade C
| Severity |
Count |
| 🔴 Critical |
0 |
| 🟠 High |
7 |
| 🟡 Medium |
0 |
| 🟢 Low |
0 |
Summary: 7 high-severity findings in the filesystem server — this server has broad filesystem access so these are worth reviewing carefully.
📋 Full report with findings and evidence: https://mcpsafe.io/registry/npm/@modelcontextprotocol/server-filesystem
Add a security badge to your README
[](https://mcpsafe.io/registry/npm/@modelcontextprotocol/server-filesystem)
This badge auto-updates whenever a new scan runs — great for showing users your security posture.
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 the @modelcontextprotocol/server-filesystem npm package 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: 68/100 · Grade C
Summary: 7 high-severity findings in the filesystem server — this server has broad filesystem access so these are worth reviewing carefully.
📋 Full report with findings and evidence: https://mcpsafe.io/registry/npm/@modelcontextprotocol/server-filesystem
Add a security badge to your README
This badge auto-updates whenever a new scan runs — great for showing users your security posture.
Feel free to close this if you're already tracking these findings. Happy to answer any questions about specific findings.
— Truong BUI · mcpsafe.io