ibmi-mcp-server
An MCP server that enables AI assistants to interact with IBM i AS/400 source members for source code management, compilation, and development workflows.
README
IBM i MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with IBM i AS/400 source members, providing seamless integration for source code management, compilation, and development workflows.
🚀 Features
- 🔗 IBM i Integration: Connect to IBM i AS/400 systems
- 📂 Source Member Management: Read, write, list, and manage source members
- 🔧 Compilation Support: Compile RPG, DDS, and other source types
- 🏷️ Automatic Source Marking: Apply source mark "5719A" to all modifications
- 🌐 MCP Protocol: Full Model Context Protocol compliance
- 🎯 AI Assistant Ready: Direct integration with ChatGPT, Claude, and other AI tools
📋 Table of Contents
⚡ Quick Start
1. Install Dependencies
git clone https://github.com/[your-username]/ibmi-mcp-server.git
cd ibmi-mcp-server
npm install
2. Build the Server
npm run build
3. Test Installation
npm test
4. Configure MCP Client
Add to your MCP client configuration:
{
"mcpServers": {
"ibmi-mcp-server": {
"command": "node",
"args": ["path/to/ibmi-mcp-server/build/index.js"]
}
}
}
5. Start Using
Connect to your IBM i system and start managing source members through your AI assistant!
🛠 Installation
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
# Clone the repository
git clone https://github.com/[your-username]/ibmi-mcp-server.git
cd ibmi-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
# Run tests
npm test
# Start development mode (with auto-reload)
npm run dev
Production Deployment
# Install production dependencies only
npm ci --production
# Build for production
npm run build
# Start the server
npm start
⚙️ Configuration
Environment Variables
Create a .env file in the project root:
# Default IBM i connection settings
DEFAULT_IBMI_HOST=your-ibmi-system.com
DEFAULT_IBMI_USER=your-username
DEFAULT_LIBRARY=QGPL
DEFAULT_SOURCE_FILE=QRPGLESRC
# Development settings
NODE_ENV=development
DEBUG=false
MCP Client Integration
For VS Code with MCP Extension
Add to your VS Code settings or MCP configuration file:
{
"mcpServers": {
"ibmi-mcp-server": {
"command": "node",
"args": ["C:\\path\\to\\ibmi-mcp-server\\build\\index.js"],
"env": {
"NODE_ENV": "production"
}
}
}
}
For Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"ibmi": {
"command": "node",
"args": ["path/to/ibmi-mcp-server/build/index.js"]
}
}
}
🔧 Tools Reference
connect_ibmi
Connect to an IBM i AS/400 system.
Parameters:
host(string, required): IBM i system hostname or IPuser(string, required): User profile namepassword(string, optional): Passwordport(number, default: 23): Connection portlibrary(string, default: "QGPL"): Default librarysourceFile(string, default: "QRPGLESRC"): Default source file
Example:
{
"host": "ibmi-system.company.com",
"user": "DEVELOPER",
"library": "MYLIB",
"sourceFile": "QRPGLESRC"
}
list_source_members
List source members with optional filtering.
Parameters:
library(string, optional): Library namesourceFile(string, optional): Source physical file namemember(string, optional): Member name patterntype(string, optional): Source type filter (RPGLE, DSPF, etc.)
Example:
{
"library": "MYLIB",
"sourceFile": "QRPGLESRC",
"type": "RPGLE"
}
read_source_member
Read source member content with optional line range.
Parameters:
member(string, required): Source member namelibrary(string, optional): Library namesourceFile(string, optional): Source file namestartLine(number, optional): Starting line numberendLine(number, optional): Ending line number
Example:
{
"member": "MYPROG",
"startLine": 1,
"endLine": 100
}
write_source_member
Write or update source member with automatic "5719A" source marking.
Parameters:
member(string, required): Source member namecontent(string, required): Source member contentlibrary(string, optional): Library namesourceFile(string, optional): Source file namesourceType(string, optional): Source type (RPGLE, DSPF, etc.)description(string, optional): Member description
Example:
{
"member": "MYPROG",
"content": "// RPG code here...",
"sourceType": "RPGLE",
"description": "Updated by AI assistant"
}
compile_source_member
Compile a source member.
Parameters:
member(string, required): Source member namelibrary(string, optional): Library namesourceFile(string, optional): Source file namesourceType(string, optional): Source typeoptions(string, optional): Compile options
Example:
{
"member": "MYPROG",
"sourceType": "RPGLE",
"options": "OPTION(*EVENTF)"
}
📚 Resources
Source Member Resource
Access IBM i source members as MCP resources using URI templates:
URI Pattern: ibmi://source/{library}/{sourceFile}/{member}
Examples:
ibmi://source/MYLIB/QRPGLESRC/MYPROGibmi://source/TESTLIB/QDDSSRC/MYDSPFibmi://source/PRODLIB/QCPYSRC/MYCPY
💡 Examples
Example 1: Connect and List Members
// Connect to IBM i
await callTool("connect_ibmi", {
host: "ibmi-system.company.com",
user: "DEVELOPER",
library: "MYLIB"
});
// List RPG source members
const members = await callTool("list_source_members", {
type: "RPGLE"
});
Example 2: Read and Modify Source
// Read existing source member
const source = await callTool("read_source_member", {
member: "MYPROG"
});
// Modify the source (add your changes)
const updatedSource = source.content + "\n// Added by AI assistant";
// Write back with automatic source marking
await callTool("write_source_member", {
member: "MYPROG",
content: updatedSource,
sourceType: "RPGLE",
description: "Enhanced by AI"
});
Example 3: Compile and Check Results
// Compile the source member
const compileResult = await callTool("compile_source_member", {
member: "MYPROG",
sourceType: "RPGLE"
});
console.log("Compilation:", compileResult.success ? "SUCCESS" : "FAILED");
Example 4: Using Resources
// Access source member as a resource
const resource = await readResource("ibmi://source/MYLIB/QRPGLESRC/MYPROG");
console.log("Source content:", resource.contents[0].text);
🏗 Development
Development Scripts
# Start development mode with auto-reload
npm run dev
# Build the project
npm run build
# Run the server
npm start
# Run tests
npm test
# Lint code
npm run lint
# Open MCP Inspector (if installed)
npm run inspector
Adding New Tools
- Define the tool in
src/index.ts:
server.registerTool(
"my_new_tool",
{
description: "Description of what the tool does",
inputSchema: {
parameter1: z.string().describe("Parameter description"),
parameter2: z.number().optional().describe("Optional parameter"),
},
},
async ({ parameter1, parameter2 }) => {
// Tool implementation
return {
content: [
{
type: "text",
text: `Result: ${parameter1}`,
},
],
};
}
);
- Build and test:
npm run build
npm test
VS Code Development
The project includes VS Code configuration for debugging:
- Open project in VS Code
- Set breakpoints in source code
- Press F5 to start debugging
- Use the Debug Console to interact with the server
🔒 Security Considerations
- Never commit credentials to version control
- Use environment variables for sensitive configuration
- Implement proper IBM i user permissions
- Validate all input parameters
- Use secure connection methods for IBM i access
📄 Source Marking
All source modifications automatically receive the "5719A" source mark:
- RPG Sources: Mark applied at position 75+
- DDS Sources: Mark applied at position 81+
- Other Sources: Mark applied at appropriate position based on source type
This ensures compliance with source marking standards and tracks AI-assisted modifications.
🐛 Troubleshooting
Common Issues
Build fails with module errors:
npm install
npm run build
Server won't connect to IBM i:
- Check host/port settings
- Verify user credentials
- Ensure network connectivity
Source marking issues:
- Source mark "5719A" is applied automatically
- Check line length limits for your source type
MCP client connection issues:
- Verify the correct path to build/index.js
- Check Node.js version (18.0.0+ required)
- Ensure the server builds successfully
Debug Mode
Run with verbose logging:
DEBUG=* npm start
Getting Help
- 📖 Documentation: See DEVELOPMENT_GUIDE.md
- 🐛 Issues: GitHub Issues
- 💬 Discussions: GitHub Discussions
🤝 Contributing
We welcome contributions! Please see our Contributing Guide for details.
Quick Contribution Steps
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Make your changes
- Add tests if applicable
- Run quality checks:
npm run lint && npm test - Commit changes:
git commit -m "Add amazing feature" - Push to branch:
git push origin feature/amazing-feature - Open a Pull Request
📜 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Model Context Protocol team for the excellent SDK
- IBM i community for inspiration and requirements
- VS Code and TypeScript teams for amazing developer tools
🌟 Star History
If this project helps you, please consider giving it a star! ⭐
Built with ❤️ for the IBM i community
Enable your AI assistants to work directly with IBM i AS/400 source members while maintaining professional source marking standards.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.