IBM i MCP Server

--- title: "IBM i MCP Server" description: "Connect AI agents to IBM i systems through secure, YAML-configured SQL tools with enterprise authentication and observability." --- A production-ready **Model Context Protocol (MCP) server** for IBM i.  --- ## What is This? The IBM i MCP Server transforms your IBM i SQL expertise into AI-accessible tools: - **SQL → AI Tools**: Write SQL in YAML files, get AI-ready tools automatically - **Zero Code**: No TypeScript, no REST APIs—just SQL you already know - **Secure by Default**: IBM i authorities, parameter binding, audit trails built-in - **Universal Protocol**: Works with 10+ AI clients (Claude Desktop, VSCode, Cursor, etc.) **Example**: A 10-line YAML file defining a "system status" query becomes a tool that AI agents can discover, understand, and execute—with built-in validation and formatting. --- ## Quick Start Path <Steps> <Step title="Understand MCP (5 minutes)"> New to the Model Context Protocol? Read [What is MCP?](/concepts/mcp-overview) to understand how AI agents connect to IBM i. **Already familiar?** Skip to Step 2. </Step> <Step title="Install Mapepire"> Install [Mapepire](/setup-mapepire) on your IBM i system—the database connectivity layer required for MCP. **Already installed?** Verify it's running and note the port (default: 8076). </Step> <Step title="Quick Start (15 minutes)"> Follow the [Quick Start Guide](/quickstart) to install the server, configure your connection, and execute your first tool. **Result**: A working MCP server connected to your IBM i system. </Step> <Step title="Connect a Client"> Choose an AI client and connect it to your server: - [Claude Desktop](/clients/claude-desktop) - Most popular, easiest setup - [VSCode](/clients/vscode) - For development workflows - [Claude Code](/clients/claude-code) - CLI and automation - [See all 10+ clients](/clients/overview) </Step> </Steps> <Tip> **Time to First Query**: Following this path takes 30-40 minutes from start to your first successful AI-powered IBM i query. </Tip> --- ## Choose Your Path Different goals? Jump directly to what you need: <CardGroup cols={3}> <Card title="🚀 I'm New Here" icon="rocket" href="/quickstart"> **Start from scratch** Install the server, connect to IBM i, and execute your first tool in 30 minutes. → [Quick Start Guide](/quickstart) </Card> <Card title="🔧 Build SQL Tools" icon="database" href="/sql-tools/overview"> **Make data AI-accessible** Already have the server running? Learn to create custom SQL tools using YAML. → [SQL Tools Guide](/sql-tools/overview) </Card> <Card title="🤖 Build AI Agents" icon="robot" href="/agents/building-agents"> **Create specialized agents** Build intelligent IBM i agents that understand system monitoring, security, and more. → [Agent Development](/agents/building-agents) </Card> </CardGroup> --- ## Core Features <CardGroup cols={2}> <Card title="Zero-Code SQL Tools" icon="wand-magic-sparkles"> **Create database operations in minutes** Define tools using simple YAML—no TypeScript or programming required. Built-in parameter validation, SQL injection prevention, and result formatting. [Learn SQL Tools →](/sql-tools/overview) </Card> <Card title="Enterprise Security" icon="shield-halved"> **IBM i security integration** Respects user profiles, object authorities, and audit requirements. Multiple auth modes including IBM i HTTP authentication with RSA encryption. [See Configuration →](/configuration) </Card> <Card title="Multiple AI Clients" icon="plug"> **Works with your tools** Connect Claude Desktop, VSCode, Cursor, Gemini CLI, Cline, and more. Supports both stdio (development) and HTTP (production) transports. [View Clients →](/clients/overview) </Card> <Card title="Production Ready" icon="gauge-high"> **Built for enterprise IBM i** OpenTelemetry observability, structured logging, connection pooling, error handling, and comprehensive audit trails. [Review Architecture →](/concepts/architecture) </Card> </CardGroup> --- ## Key Concepts <AccordionGroup> <Accordion title="What is the Model Context Protocol (MCP)?" icon="circle-info"> MCP is an open standard that enables AI agents to securely access and interact with your data through a universal interface. Instead of building custom integrations for each AI tool, MCP provides a standardized way for any MCP-compatible agent to access your IBM i systems. **Key Benefits:** - 🔒 Secure, controlled access to enterprise data - 🔌 Universal protocol understood by all MCP clients - 🛡️ Preserves IBM i security and audit requirements - ⚡ Real-time data access without ETL or data exports [Read the full MCP overview →](/concepts/mcp-overview) </Accordion> <Accordion title="Why SQL as MCP Tools?" icon="database"> The IBM i MCP Server's core innovation is **transforming SQL queries into MCP tools** that AI agents can discover and use. This approach is ideal for IBM i because: - **Zero Code Required**: Define tools in YAML files - **IBM i Native**: Direct access to DB2, QSYS2 services, stored procedures - **Security Built-In**: Parameter binding prevents SQL injection automatically - **Rapid Development**: Create new tools in minutes **Example**: A simple SQL query becomes a discoverable, validated, secure tool that AI agents can call naturally. [Learn about SQL Tools →](/sql-tools/overview) </Accordion> <Accordion title="How does authentication work?" icon="key"> The server supports multiple authentication modes to fit your deployment: **For Development:** - **Shared credentials** (stdio): All operations use same Db2i user - Fast setup for testing and local development **For Production:** - **Per-user authentication** (HTTP): Each user connects with their own credentials - **IBM i HTTP Auth**: RSA-encrypted credential exchange - **JWT/OAuth**: Custom authentication systems All modes respect IBM i object authorities and maintain audit trails. [See authentication setup →](/configuration#authentication-settings) </Accordion> <Accordion title="What can I build with this?" icon="lightbulb"> The server enables AI agents to perform any database operation you configure: **Common Use Cases:** - 📊 System monitoring and performance analysis - 🔍 Business data queries and reporting - 🔐 Security audits and compliance checks - 📦 Inventory and resource management - 🧪 Development and debugging tools **Example Agents:** - Performance monitoring agent tracking CPU, memory, jobs - Discovery agent analyzing schemas and dependencies - Business intelligence agent answering data questions - System administration agent managing resources [Explore agent examples →](/agents/building-agents) </Accordion> </AccordionGroup> --- ## Common Questions <AccordionGroup> <Accordion title="Will this work with my IBM i version?" icon="server"> The server works with any IBM i version that supports: - DB2 for i (Db2 for IBM i) - QSYS2 system services - Mapepire server for WebSocket connectivity Tested on IBM i 7.3+, but should work on older versions with proper DB2 support. </Accordion> <Accordion title="Do I need to know TypeScript?" icon="code"> **No!** The SQL Tools system uses simple YAML configuration files. You only need SQL knowledge to create database operations. TypeScript is only required if you want to create custom tool types beyond SQL operations. </Accordion> <Accordion title="How is this different from REST APIs?" icon="question"> **MCP Advantages:** - AI agents discover tools automatically (no hardcoded endpoints) - Built-in validation and security patterns - Universal protocol works with any MCP client - Structured responses optimized for AI consumption **REST APIs require:** - Custom integration code for each AI tool - Manual endpoint documentation - Custom authentication per client - Response parsing and adaptation </Accordion> <Accordion title="Can I use this in production?" icon="shield-check"> **Yes!** The server includes production-ready features: - OpenTelemetry observability - Comprehensive audit logging - Connection pooling - Error handling and categorization - Rate limiting and resource protection - Multi-environment configuration Use HTTP transport with IBM i authentication for production deployments. </Accordion> <Accordion title="Where do I get help?" icon="life-ring"> **Resources:** - 📖 Documentation: You're reading it! - 💬 GitHub Issues: [Report bugs or request features](https://github.com/IBM/ibmi-mcp-server/issues) - 🔧 Configuration: See [environment variables](/configuration) - 🚀 Examples: Review [SQL tools](/sql-tools/building-tools) and [agents](/agents/building-agents) </Accordion> </AccordionGroup> --- ## Ready to Start? <CardGroup cols={2}> <Card title="Quick Start Guide" icon="rocket" href="/quickstart"> **15-minute setup** Install, configure, and execute your first tool </Card> <Card title="SQL Tools Tutorial" icon="database" href="/sql-tools/building-tools"> **Build custom tools** Transform SQL into AI-accessible operations </Card> </CardGroup> ### More Resources - [What is MCP?](/concepts/mcp-overview) - Understand the protocol - [Configuration Reference](/configuration) - All environment variables - [Client Integrations](/clients/overview) - Connect your AI client - [Agent Development](/agents/building-agents) - Build specialized agents --- <Note> **About This Project**: The IBM i MCP Server is an open-source project that brings modern AI agent capabilities to IBM i environments while maintaining enterprise security and operational standards. Contributions and feedback are welcome on [GitHub](https://github.com/IBM/ibmi-mcp-server). </Note>