AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall for LangChain
dev.agentdiet/prompt-guard
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
client:LangChain
transport:streamable-http
tools:2
Install AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"prompt-guard": {
"transport": "streamable_http",
"url": "https://prompt-guard.agentdiet.dev/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs