claude mcp add etri-metrillm -- npx -y metrillm-mcp
{
"mcpServers": {
"etri-metrillm": {
"command": "npx",
"args": ["-y", "metrillm-mcp"]
}
}
}
{
"mcpServers": {
"etri-metrillm": {
"command": "npx",
"args": ["-y", "metrillm-mcp"]
}
}
}
{
"mcpServers": {
"etri-metrillm": {
"command": "npx",
"args": ["-y", "metrillm-mcp"]
}
}
}
About This MCP Server
The MetriLLM Model Context Protocol server is a developer tool that enables benchmarking of local large language models, providing assessments of their speed, quality, and hardware fitness. It connects to any MCP client and can be installed via npm, utilizing stdio for communication. Developers would use this tool to evaluate the performance of their local models, likely during the development or testing phases of their projects.
Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client. This is a Model Context Protocol (MCP) server that extends AI assistants like Claude with developer tools capabilities via the stdio transport.
Package
metrillm-mcp on npm
HOW TO USE
Select your AI client above to get the install command. This MCP server uses the stdio transport and is available on npm.
What tools does it provide?
The metrillm server extends your AI assistant with developer tools capabilities. Once installed, your AI can use its tools automatically.
