coding agent audit for LangChain
io.github.stackscribe-ai/coding-agent-audit
Audits Claude Code/Cursor MCP configs for supply-chain backdoors and risky permissions.
client:LangChain
transport:stdio
runtime:pypi
Install coding agent audit in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"coding-agent-audit": {
"transport": "stdio",
"command": "uvx",
"args": ["coding-agent-audit"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs