NestDaddy
All servers NestDaddy MCP Blog Sign inTry it free
AI and media

Inferbench

io.github.RudrenduPaul/inferbench · v0.1.7

Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.

Source code Set it up

Connect Runs on your machine

Terminal
claude mcp add inferbench -- uvx inferbench-cli==0.1.7
claude_desktop_config.json
{
  "mcpServers": {
    "inferbench": {
      "command": "uvx",
      "args": [
        "inferbench-cli==0.1.7"
      ]
    }
  }
}
~/.cursor/mcp.json
{
  "mcpServers": {
    "inferbench": {
      "command": "uvx",
      "args": [
        "inferbench-cli==0.1.7"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "inferbench": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "inferbench-cli==0.1.7"
      ]
    }
  }
}

Tools

This server runs locally, so its tools are listed by your MCP client once it starts.

Details

Package[email protected] (PYPI, stdio)
First published11 Aug 2026
Last updated11 Aug 2026
Registry nameio.github.RudrenduPaul/inferbench

More ai and media servers See all

Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.