ibmi

This MCP server provides a bridge between your AI assistant and IBM i AS/400 systems. It exposes tools to connect to an IBM i, read and write source members, list and filter members, and compile sources, all wrapped in the MCP (Model Context Protocol) interface. You can use it from an AI assistant like ChatGPT or Claude by calling the registered tools such as connect_ibmi, list_source_members, read_source_member, write_source_member, and compile_source_member. The server also automatically applies the 5719A source marking to modifications, helping you track changes across your development workflow. By leveraging MCP resources, IBM i source members are accessible as URIs (ibmi://source/{library}/{sourceFile}/{member}) for seamless integration with your tooling.

Typical usage flows include: connecting to your IBM i system, listing and retrieving source members, editing and saving changes with automatic marking, and compiling to verify changes. You can chain these tools in a single AI session to implement development tasks, refactor code, or perform quick iterations against IBM i sources.

When configuring clients, you can point the MCP client to the server entry (for example ibmi-mcp-server) and invoke the tools with appropriate parameters. The Tools Reference section of the README documents the required and optional parameters for each tool, enabling precise control from your assistant.

Prerequisites

• Node.js 18.0.0 or higher
• npm (comes with Node.js)
• Access to IBM i AS/400 system
• MCP-compatible AI assistant or client

Local Development Setup

1. Clone the repository git clone https://github.com/[your-username]/ibmi-mcp-server.git cd ibmi-mcp-server

2. Install dependencies npm install

3. Build the project npm run build

4. Run tests npm test

5. Start development mode (with auto-reload) npm run dev

Production Deployment

1. Install production dependencies only npm ci --production

2. Build for production npm run build

3. Start the server npm start

Configuration tips

• Ensure your .env (or environment) contains IBM i connection defaults if you want to pre-configure connections: DEFAULT_IBMI_HOST=your-ibmi-system.com DEFAULT_IBMI_USER=your-username DEFAULT_LIBRARY=QGPL DEFAULT_SOURCE_FILE=QRPGLESRC
• You can customize environment variables for different environments (e.g., NODE_ENV, DEBUG) as needed.

Tips and common considerations:

• The server exposes tools to manage and manipulate IBM i source members (read, write with automatic 5719A marking, list, and compile). Use the MCP URI resources ibmi://source/{library}/{sourceFile}/{member} to reference members in your tooling.
• For VS Code integration, you can configure the MCP server in your settings and pass an index.js path to run the server in production or development modes.
• If you encounter connection issues, verify network access to the IBM i host, correct user permissions, and that the IBM i subsystem is accessible on the expected port.
• The write_source_member tool enforces automatic source marking; ensure your content is valid for the target source type (RPGLE, DSPF, etc.).
• When deploying, consider using production builds only and restricting DEBUG or verbose logging in production to avoid exposing sensitive information.
• The Tools Reference section documents each tool’s required and optional parameters; use those to construct precise tool calls from your AI assistant.