metrillm for LangChain
io.github.metrillm/metrillm
Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
client:LangChain
transport:stdio
runtime:npm
Install metrillm in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"metrillm": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "metrillm-mcp"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs