Locust

🚀 Local Group Load Testing MCP Server

This is a Model Context Protocol (MCP) server implementation for load testing based on Locust. The server seamlessly integrates Locust load testing capabilities with an AI-driven development environment.

✨ Features

• Simple integration of the Model Context Protocol framework.
• Supports both headless and GUI modes.
• Configurable test parameters (number of users, spawn rate, run time).
• A simple API for running Locust load tests.
• Real-time test execution output.
• Native support for HTTP/HTTPS protocols.
• Supports custom task scenarios.

🔧 Prerequisites

Before you start, make sure you have the following installed:

• Python 3.13 or higher.
• The uv package manager (Installation Guide).

📦 Installation

1. Clone the repository:

git clone https://github.com/qainsights/locust-mcp-server.git

2. Install the required dependencies:

uv pip install -r requirements.txt

3. Set environment variables (optional): Create a .env file in the project root directory:

LOCUST_HOST=http://localhost:8089  # Default test host
LOCUST_USERS=3                     # Default number of users
LOCUST_SPAWN_RATE=1               # User spawn rate
LOCUST_RUN_TIME=10s               # Default test duration

🚀 Quick Start

1. Create a Locust test script (e.g., hello.py):

from locust import HttpUser, task, between

class QuickstartUser(HttpUser):
    wait_time = between(1, 5)

    @task
    def hello_world(self):
        self.client.get("/hello")
        self.client.get("/world")

    @task(3)
    def view_items(self):
        for item_id in range(10):
            self.client.get(f"/item?id={item_id}", name="/item")
            time.sleep(1)

    def on_start(self):
        self.client.post("/login", json={"username":"foo", "password":"bar"})

2. Configure the MCP server in your preferred MCP client (Claude Desktop, Cursor, Windsurf, etc.) with the following configuration:

{
  "mcpServers": {
    "locust": {
      "command": "/Users/naveenkumar/.local/bin/uv",
      "args": [
        "--directory",
        "/Users/naveenkumar/Gits/locust-mcp-server",
        "run",
        "locust_server.py"
      ]
    }
  }
}

3. Now, let the large language model run the test, for example: Run the Locust test to analyze hello.py. The Locust MCP server will use the following tool to start the test:

• run_locust: Runs the test according to the configuration options (including headless mode, host, duration, number of users, and spawn rate).

💻 Usage Examples

Basic Usage

from locust import HttpUser, task, between

class QuickstartUser(HttpUser):
    wait_time = between(1, 5)

    @task
    def hello_world(self):
        self.client.get("/hello")
        self.client.get("/world")

    @task(3)
    def view_items(self):
        for item_id in range(10):
            self.client.get(f"/item?id={item_id}", name="/item")
            time.sleep(1)

    def on_start(self):
        self.client.post("/login", json={"username":"foo", "password":"bar"})

📚 Documentation

Run Locust Test

run_locust(
    test_file: str,
    headless: bool = True,
    host: str = "http://localhost:8089",
    runtime: str = "10s",
    users: int = 3,
    spawn_rate: int = 1
)

Parameter Description:

• test_file: Path to the Locust test script.
• headless: Whether to run in headless mode (True) or with a GUI (False).
• host: Default test host address.
• runtime: Default test duration.
• users: Default number of users.
• spawn_rate: User spawn rate.

✨ Use Cases

• Performance Testing: Simulate high-concurrency access scenarios by configuring different numbers of users and spawn rates.
• Stability Testing: Verify the system's stability and responsiveness under extreme loads.
• Stress Testing: Identify system bottlenecks and evaluate its ability to withstand stress.

⚠️ Important Note

• Ensure that the installed Python version meets the requirements (3.13 or higher).
• When running high-load tests, it is recommended to monitor system resource usage.
• If you encounter performance issues, consider optimizing the code or increasing hardware resources.

By following the above steps, you can easily configure and run Locust-based load tests and integrate them into an AI-driven development environment.