Skip to content
mcp/harbor
LangChain

Inference AIops for LangChain

io.github.aiops-tools/inference-aiops

Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.

client:LangChain transport:stdio runtime:pypi

Install Inference AIops in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "inference-aiops": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["inference-aiops"],
        }
})

tools = await client.get_tools()

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

Inference AIops in other clients

Inference AIops MCP server