Skip to content
mcp/harbor
LangChain

agentshield mcp for LangChain

io.github.dl-eigenart/agentshield-mcp

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

client:LangChain transport:stdio runtime:npm

Install agentshield mcp in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

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

tools = await client.get_tools()

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

agentshield mcp in other clients

agentshield mcp MCP server