Skip to content
mcp/harbor
LangChain

threat rules for LangChain

io.github.guardbee/threat-rules

GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection

client:LangChain transport:stdio runtime:npm

Install threat rules in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "threat-rules": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "@guardbee/mcp-threat-rules"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

threat rules in other clients

threat rules MCP server