Offense for LangChain
io.github.offense-research/offense
Security tools for coding agents: dependency advisory audits and evidence for remediation.
client:LangChain
transport:streamable-http
tools:1
Install Offense in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"offense": {
"transport": "streamable_http",
"url": "https://offense.sh/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs