Skip to content
mcp/harbor
LangChain

PromptGuard for LangChain

co.promptguard/security

Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client

client:LangChain transport:stdio runtime:npm

Install PromptGuard in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

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

tools = await client.get_tools()

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

PromptGuard in other clients

PromptGuard MCP server