Skip to content
mcp/harbor
LangChain

Sentinel Scan for LangChain

io.github.ventrova/sentinel-scan-cli

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

client:LangChain transport:stdio runtime:npm

Install Sentinel Scan in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "sentinel-scan-cli": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "sentinel-scan-cli"],
        }
})

tools = await client.get_tools()

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

Sentinel Scan in other clients

Sentinel Scan MCP server