vLLM Benchmark MCP server

This tool allows you to benchmark vLLM servers using the Model Context Protocol (MCP). It provides an interactive way to measure and compare performance of different vLLM configurations, building on established benchmarking approaches while leveraging MCP's flexibility.

Installation

To get started with the MCP vLLM Benchmarking Tool:

1. Clone the repository from GitHub (use the repository URL when available)

2. Configure the tool as an MCP server by adding it to your MCP configuration:

{
    "mcpServers": {
        "mcp-vllm": {
            "command": "uv",
            "args": [
                "run",
                "/Path/TO/mcp-vllm-benchmarking-tool/server.py"
            ]
        }
    }
}

Be sure to replace /Path/TO/mcp-vllm-benchmarking-tool/server.py with the actual path to the cloned repository's server.py file on your system.

Using the Benchmarking Tool

Once configured, you can interact with the tool through your MCP-compatible application. Send prompts that include benchmarking instructions.

Example Benchmark Request

Here's an example prompt that runs a benchmark:

Do a vllm benchmark for this endpoint: http://10.0.101.39:8888 
benchmark the following model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B 
run the benchmark 3 times with each 32 num prompts, then compare the results, but ignore the first iteration as that is just a warmup.

Parameters You Can Specify

In your prompts, you can customize:

• The vLLM endpoint URL
• The model to benchmark
• Number of test iterations
• Number of prompts per test
• Whether to ignore initial iterations (for warmup)

Known Issues

• The tool may occasionally report finding invalid JSON due to random outputs from vLLM. This is a known issue that is currently being investigated.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.