GitHub - QAInsights/jmeter-mcp-server: ✨ JMeter Meets AI Workflows: Introducing the JMeter MCP Server! 🤯 (original) (raw)

🚀 JMeter MCP Server

This is a Model Context Protocol (MCP) server that allows executing JMeter tests through MCP-compatible clients.

Important

📢 Looking for an AI Assistant inside JMeter? 🚀 Check out Feather Wand

Anthropic Cursor Windsurf

📋 Features

🛠️ Installation

Local Installation

  1. Install uv:
  2. Ensure JMeter is installed on your system and accessible via the command line.

⚠️ Important: Make sure JMeter is executable. You can do this by running:

chmod +x /path/to/jmeter/bin/jmeter

  1. Configure the .env file, refer to the .env.example file for details.

JMeter Configuration

JMETER_HOME=/path/to/apache-jmeter-5.6.3 JMETER_BIN=${JMETER_HOME}/bin/jmeter

Optional: JMeter Java options

JMETER_JAVA_OPTS="-Xms1g -Xmx2g"

💻 MCP Usage

  1. Connect to the server using an MCP-compatible client (e.g., Claude Desktop, Cursor, Windsurf)
  2. Send a prompt to the server:
Run JMeter test /path/to/test.jmx
  1. MCP compatible client will use the available tools:
    • 🖥️ execute_jmeter_test: Launches JMeter in GUI mode, but doesn't execute test as per the JMeter design
    • 🚀 execute_jmeter_test_non_gui: Execute a JMeter test in non-GUI mode (default mode for better performance)

🏗️ MCP Configuration

Add the following configuration to your MCP client config:

{ "mcpServers": { "jmeter": { "command": "/path/to/uv", "args": [ "--directory", "/path/to/jmeter-mcp-server", "run", "jmeter_server.py" ] } } }

✨ Use case

LLM powered result analysis: Collect and analyze test results.

Debugging: Execute tests in non-GUI mode for debugging.

🛑 Error Handling

The server will: