KillerSkills for LangChain
io.github.cyligence-karim/killerskills
Security verdicts for agent skills and MCP servers, from sandbox runs, before you install them.
client:LangChain
transport:stdio
runtime:npm
Install KillerSkills in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"killerskills": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "vet-skills"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs