iris-execute

The IRIS Execute MCP server provides a consolidated runtime for InterSystems IRIS development tools. It exposes eight capabilities split across basic operations, compilation utilities, and a unit testing tool, all accessible through a single Python-based MCP server. With these tools, you can execute ObjectScript commands with I/O capture, invoke class methods dynamically, read and write global values, retrieve system information, compile ObjectScript classes or packages, and run unit tests quickly using the DirectTestRunner. The server is designed to work with VS Code extensions (such as Cline) for chat-driven execution and automatic tool approval, making IRIS development and testing faster and more scriptable.

Prerequisites: Install Python 3.8+, InterSystems IRIS 2024.3 or later, and a VS Code environment with the Cline extension.

Step 1: Clone the repository and set up a virtual environment

# Clone the repository
git clone https://github.com/jbrandtmse/iris-execute-mcp.git
cd iris-execute-mcp

# Create virtual environment
python -m venv venv

# Activate virtual environment
# Windows:
venv\Scripts\activate
# Linux/macOS:
source venv/bin/activate

Step 2: Install dependencies

pip install -r requirements.txt

Step 3: Configure environment for IRIS connection (example)

IRIS_HOSTNAME=localhost
IRIS_PORT=1972
IRIS_NAMESPACE=HSCUSTOM
IRIS_USERNAME=*username*
IRIS_PASSWORD=*password*

Step 4: Prepare the MCP server script and dependencies

• Ensure iris_execute_mcp.py is present in the project root or configure the path accordingly.
• Install IRIS-specific dependencies if needed and verify Python environment is active.

Step 5: Run the MCP server for testing

python iris_execute_mcp.py

Step 6: (Optional) Integrate with VS Code Cline by adding the MCP settings in your settings.json as shown in the README.

Tips and notes:

• The server consolidates all eight tools into a single Python MCP server process for reliability. Ensure your IRIS connection details (host, port, namespace, user, password) are correct in the environment or settings.json.
• Use the autoApprove feature in Cline MCP settings to streamline workflows across the eight tools.
• When testing, verify that the IRIS connectivity test passes before attempting to run more complex commands or tests.
• If you encounter environment or path issues, ensure the virtual environment is activated and that iris_execute_mcp.py and its dependencies are accessible from the working directory.
• For performance-sensitive workflows, the DirectTestRunner enables faster unit test execution (6-21 ms range) compared to the traditional %UnitTest.Manager approach.