Five MCP security scanners on the same tool definitions
An MCP tool description can tell an assistant to change another tool's arguments, read a local file before answering, or hide an extra action. A useful scanner comparison needs to show which malicious definitions receive a signal, what happens on benign definitions, and which targets never receive a complete result. I maintain both WARDEN and HISTOR , which supplies the historical package…
The comparison of five MCP security scanners reveals that WARDEN, a tool maintained by the reporter, produced high/critical signals on 460 out of 485 served MCPTox definitions, while the remaining four scanners produced between 1 and 56 such signals. WARDEN's historical packages also generated thousands of advisory-only signals.
The comparison focuses on the published packages, verified against the registry, and includes their respective versions, package names, and SHA-256 hashes. The reported findings highlight differences in how each scanner handles various signals and policy settings, emphasizing the importance of considering all signal types rather than just high/critical ones.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.