metrillm for VS Code
io.github.metrillm/metrillm
Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
client:VS Code
transport:stdio
runtime:npm
Install metrillm in VS Code
.vscode/mcp.json
{
"servers": {
"metrillm": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"metrillm-mcp"
]
}
}
}Requires agent mode. MCP: Open User Configuration puts the same block in every workspace. VS Code docs