VulnMCP can now leverage multiple skills to classify vulnerability descriptions written in English, Russian, or Chinese.
https://github.com/vulnerability-lookup/VulnMCP
#AI #Orchestration #NLP #MCP #VulnerabilityLookup #Vulnerability #CVE #GCVE #Agentic #Python #OpenSource #Transformers
@cedric Multi-language vuln classification through MCP skills is a solid fit for composable tooling.
But when a security agent pulls in an MCP server for vuln analysis, how does it know the server is who it claims to be? There's no discovery or trust verification standard yet. The IETF agents.txt draft expires tomorrow and the 11 competing proposals have zero adoption.
Sharper tools on an unverified foundation.
Cedric
Global Chat