LangChain AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall Resource/docs-mcp-lock
How to: LangChain AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall docs-mcp-lock
Add AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall to LangChain
-
01
Open pip install langchain-mcp-adapters and merge this in. Keep any servers already there.
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()
-
02
Save the file and restart LangChain.
-
03
docs-mcp-lock is surfaced through the client's resource API, read by URI. It is context to attach, not an action to run.
-
04
If it does not appear, check that AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall is connected and that you are looking at its resources rather than its tools.
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs
Same resource, other clients
Read from the server itself, by connecting to it and calling resources/list on 19 October 2026.
A listing does not declare its resources, so asking is the only way to know them, and this
is what the server actually offers rather than what its listing claims. Names only are
stored; connect the server for each resource's type and contents.