AgentUnmask for LangChain
io.github.karansharma1732/agentunmask
Scan a URL before your agent reads it: hidden prompt injection, phishing, clean markdown.
client:LangChain
transport:streamable-http
Install AgentUnmask in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"agentunmask": {
"transport": "streamable_http",
"url": "https://agentunmask.com/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs