toxic flow auditor for LangChain
io.github.guardbee/toxic-flow-auditor
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
client:LangChain
transport:stdio
runtime:npm
Install toxic flow auditor in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"toxic-flow-auditor": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "@guardbee/mcp-toxic-flow-auditor"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs