Skip to content
MCP server

Inferbench

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

Runs locallyStatus and history
Install
Pricing
Open source
Runs
Locally
Version
0.1.7
Listing updated
6 days ago

About Inferbench

Inferbench is an open-source MCP server. It runs locally on your machine and is started by your AI client.

Install

Run in a terminal

claude mcp add inferbench -- uvx inferbench-cli

Add to claude_desktop_config.json

{
  "mcpServers": {
    "inferbench": {
      "command": "uvx",
      "args": [
        "inferbench-cli"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "inferbench": {
      "command": "uvx",
      "args": [
        "inferbench-cli"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "inferbench": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "inferbench-cli"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "inferbench": {
      "command": "uvx",
      "args": [
        "inferbench-cli"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "inferbench": {
      "command": "uvx",
      "args": [
        "inferbench-cli"
      ]
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Pricing

Open source

Inferbench FAQ

Is Inferbench free?

Yes. Inferbench is open source, so you can use and self-host it for free.

How do I add Inferbench to Claude Code?

Run this command in your terminal: claude mcp add inferbench -- uvx inferbench-cli

Where this comes from

  • Description: from the official MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers