IBM i MCP Server

MCP server for IBM i

Overview

The IBM i MCP Server enables AI agents to interact with IBM i systems through the Model Context Protocol (MCP). It provides secure, SQL-based access to Db2 for i databases, allowing AI applications like Claude, VSCode Copilot, Bob, and custom agents to query system information, monitor performance, and execute database operations.

How it works: AI clients connect via MCP → Server executes YAML-defined SQL tools → Results stream back to the AI agent through Mapepire.

📁 Repository Structure

📖 Quick Navigation

• 🚀 MCP Server - Get started with the server

• 🧩 SQL Tools - Create custom SQL tools

• 🤖 AI Agents - Use agent frameworks

• 🐍 Python Clients - Test with Python clients

• 📦 Deployment - Deploy to production

• 📡 Setup Mapepire - Install prerequisite

🚀 MCP Server

The MCP Server enables AI agents to execute SQL queries on IBM i systems through YAML-defined SQL tools.

Quick Start

Prerequisites:

• Mapepire running on IBM i (port 8076)

• Node.js 18+ installed

Get Started:

1. Clone the repository:

   git clone https://github.com/IBM/ibmi-mcp-server.git cd ibmi-mcp-server

2. Configure your IBM i connection:

   cat > .env << 'EOF' DB2i_HOST=your-ibmi-host.com DB2i_USER=your-username DB2i_PASS=your-password DB2i_PORT=8076 DB2i_IGNORE_UNAUTHORIZED=true EOF

3. Start the server:

   npx -y @ibm/ibmi-mcp-server@latest \ --transport http \ --tools ./tools/performance/performance.yaml

   The server will use our pre-configured tools for:

   • 📊 Performance monitoring (system status, memory pools, active jobs)

   • See the Tools Guide for more toolsets.

4. Verify it's running:

   # Check server health curl http://localhost:3010/healthz # List available tools curl -X POST http://localhost:3010/mcp \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | \ grep -o '"name":"[^"]*"' | sed 's/"name":"//g' | sed 's/"//g' | head -20

🧩 SQL Tools

YAML-based SQL tool configurations that define what queries AI agents can execute on your IBM i system.

Quick Start

Create a custom tool file tools/my-tools.yaml:

Run the server with your tools:

Available Tool Collections

The tools/ directory includes ready-to-use configurations:

• Performance Monitoring - System status, active jobs, CPU/memory metrics

• Security & Audit - User profiles, authorities, security events

• Job Management - Active jobs, job queues, subsystems

• Storage & IFS - Disk usage, IFS objects, save files

• Database - Tables, indexes, constraints, statistics

🤖 AI Agents

Pre-built AI agent examples using popular frameworks to interact with IBM i systems through the MCP Server.

Available Agent Frameworks

What Agents Can Do

• System Monitoring: Real-time performance analysis and health checks

• Troubleshooting: Diagnose issues using natural language queries

• Reporting: Generate system reports and insights

• Automation: Execute administrative tasks through conversation

🐍 Python Clients

Simple Python client examples for testing and interacting with the MCP Server.

📦 Deployment

Production-ready deployment configurations for containerized environments.

Deployment Options

• Docker & Podman - Complete stack with MCP Context Forge Gateway

• OpenShift - Kubernetes deployment with S2I builds

• Production Features - HTTPS, authentication, monitoring, caching

📡 Setup Mapepire

Before you can use the ibmi-mcp-server, you must install and configure Mapepire on your IBM i system.

What is Mapepire?

Mapepire is a modern, high-performance database server for IBM i that provides SQL query execution capabilities over WebSocket connections. It acts as a gateway between modern application architectures (like MCP servers, AI agents, and REST APIs) and IBM i's Db2 for i database.

Why Mapepire Enables AI and MCP Workloads

Traditional IBM i database access methods (ODBC, JDBC) don't align well with modern AI and MCP architectures that require:

• Fast, lightweight connections: AI agents make frequent, short-lived database queries

• WebSocket support: Enables real-time, bidirectional communication for streaming results

• Modern JSON-based protocols: Simplifies integration with TypeScript/JavaScript ecosystems

• Low-latency responses: Essential for interactive AI conversations and tool executions

Mapepire bridges this gap by providing a modern, WebSocket-based SQL query interface that's optimized for the request/response patterns of AI agents and MCP tools.

Installation

Quick Install (IBM i SSH Session):

📜 License

This project is licensed under the Apache License 2.0. See the LICENSE file for details.