memory poisoning scanner for LangChain
io.github.guardbee/memory-poisoning-scanner
Scans agent code for untrusted input poisoning persistent cross-session memory
client:LangChain
transport:stdio
runtime:npm
Install memory poisoning scanner in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"memory-poisoning-scanner": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "@guardbee/mcp-memory-poisoning-scanner"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs