Skip to main content
Glama
Narasimhakatta

JMeter MCP Server

execute_jmeter_test

Run JMeter performance tests from JMX files to evaluate application load and response times. Supports GUI mode for test monitoring and analysis.

Instructions

Execute a JMeter test.

Args: test_file: Path to the JMeter test file (.jmx) gui_mode: Whether to run in GUI mode (default: False)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
test_fileYes
gui_modeNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Primary handler for the 'execute_jmeter_test' tool. Registered with @mcp.tool() decorator. Handles input parameters and delegates to the run_jmeter helper function.
    @mcp.tool()
    async def execute_jmeter_test(test_file: str, gui_mode: bool = False) -> str:
        """Execute a JMeter test.
    
        Args:
            test_file: Path to the JMeter test file (.jmx)
            gui_mode: Whether to run in GUI mode (default: False)
        """
        return await run_jmeter(test_file, non_gui=not gui_mode)  # Run in non-GUI mode by default
  • Core helper function that performs file validation, constructs the JMeter subprocess command, executes it, and handles output/errors for both GUI and non-GUI modes.
    async def run_jmeter(test_file: str, non_gui: bool = True) -> str:
        """Run a JMeter test.
    
        Args:
            test_file: Path to the JMeter test file (.jmx)
            non_gui: Run in non-GUI mode (default: True)
    
        Returns:
            str: JMeter execution output
        """
        try:
            # Convert to absolute path
            test_file_path = Path(test_file).resolve()
            
            # Validate file exists and is a .jmx file
            if not test_file_path.exists():
                return f"Error: Test file not found: {test_file}"
            if not test_file_path.suffix == '.jmx':
                return f"Error: Invalid file type. Expected .jmx file: {test_file}"
    
            # Get JMeter binary path from environment
            jmeter_bin = os.getenv('JMETER_BIN', 'jmeter')
            java_opts = os.getenv('JMETER_JAVA_OPTS', '')
    
            # Log the JMeter binary path and Java options
            logger.info(f"JMeter binary path: {jmeter_bin}")
            logger.debug(f"Java options: {java_opts}")
    
            # Build command
            cmd = [str(Path(jmeter_bin).resolve())]
            
            if non_gui:
                cmd.extend(['-n'])
            cmd.extend(['-t', str(test_file_path)])
    
            # Log the full command for debugging
            logger.debug(f"Executing command: {' '.join(cmd)}")
            
            if non_gui:
                # For non-GUI mode, capture output
                result = subprocess.run(cmd, capture_output=True, text=True)
                
                # Log output for debugging
                logger.debug("Command output:")
                logger.debug(f"Return code: {result.returncode}")
                logger.debug(f"Stdout: {result.stdout}")
                logger.debug(f"Stderr: {result.stderr}")
    
                if result.returncode != 0:
                    return f"Error executing JMeter test:\n{result.stderr}"
                
                return result.stdout
            else:
                # For GUI mode, start process without capturing output
                subprocess.Popen(cmd)
                return "JMeter GUI launched successfully"
    
        except Exception as e:
            return f"Unexpected error: {str(e)}"
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but offers minimal behavioral insight. It mentions GUI mode but doesn't disclose execution behavior (e.g., blocking vs. async, output location, error handling, or system requirements). This is inadequate for a tool that likely performs system-level operations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by parameter explanations in a structured 'Args:' section. It's efficient with no wasted sentences, though the parameter details could be more integrated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (executing external tests), no annotations, and an output schema (which reduces need to describe returns), the description is minimally complete. It covers what the tool does and parameters but misses critical context like execution environment, side effects, or error scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds basic meaning for both parameters (test_file path and gui_mode boolean with default), but lacks details like file format expectations, GUI mode implications, or path resolution. This partially addresses the schema gap but remains vague.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Execute') and resource ('JMeter test'), making the purpose immediately understandable. It distinguishes from the sibling tool 'execute_jmeter_test_non_gui' by mentioning GUI mode as an option, though not explicitly contrasting them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage through the mention of GUI mode and the sibling tool name, suggesting this tool can run tests in either GUI or non-GUI mode. However, it lacks explicit guidance on when to use this vs. the sibling tool or any prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Narasimhakatta/MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server