Ibmi MCP Server

🚀 ibmi-mcp-server

MCP server for IBM i

This project provides an MCP server tailored for IBM i systems, offering seamless integration and efficient operation. It supports various transport modes and session configurations, making it suitable for different development and deployment scenarios.

📚 Documentation | ⚠️ Docs are under active development

🚀 Quick Start

1. Installation

Clone the repository and install dependencies:

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

2. Build the Project

npm run build
# Or use 'npm run rebuild' for a clean install

3. Create Server .env File

cp .env.example .env

Fill out the Db2 for i connection details in the .env file:

# IBM i DB2 for i Connection Settings
# Required for YAML SQL tools to connect to IBM i systems
DB2i_HOST=
DB2i_USER=
DB2i_PASS=
DB2i_PORT=8076
DB2i_IGNORE_UNAUTHORIZED=true

See more on configuration options in the Configuration section.

4. Running the Server

• Via Stdio (Default):

npm run start:stdio

• Via Streamable HTTP:

npm run start:http

By Default, the server registers SQL tools stored in the prebuiltconfigs directory. This path is set in the .env file (TOOLS_YAML_PATH). You can override the SQL tools path using the CLI:

• CLI Option: --tools <path>

npm run start:http -- --tools <path>

• Transport Options: --transport <type>

npm run start:http -- --transport http # or stdio

5. Run Example Agent

Make sure that the server is running in http mode:

npm run start:http

In another terminal, navigate to the tests/agents directory and follow the setup instructions in the README.

Run the example Agent:

cd tests/agents
export OPENAI_API_KEY=your_open_ai_key
uv run agent.py -p "What is my system status?"

Run the Example Scripts:

cd tests/agents

# See a list of configured tools:
uv run test_tool_annotations.py

# see a list of server resources:
uv run test_toolset_resources.py

Note: test_tool_annotations.py and run test_toolset_resources.py DO NOT require and OpenAI API Key

6. Running Tests

This template uses Vitest for testing, with a strong emphasis on integration testing to ensure all components work together correctly.

• Run all tests once:

npm test

• Run tests in watch mode:

npm run test:watch

• Run tests and generate a coverage report:

npm run test:coverage

✨ Features

• Multiple Transport Modes: Supports both stdio and http transport modes for flexible connectivity.
• Session Configuration: Allows for different session modes (stateless, stateful, or auto) in HTTP transport.
• IBM i Agents: Specialized components for seamless interaction with IBM i systems, offering real-time monitoring and management capabilities.
• SQL Tool Configuration: Configurable through tools.yaml files, enabling easy setup of data sources, tools, and toolsets.
• IBM i HTTP Authentication: Provides secure token-based access for authenticated SQL tool execution.
• Container Deployment: Supports Docker and Podman for easy deployment and management.
• Comprehensive Error Handling: Ensures reliable operation with a structured error-handling strategy.
• Observability: Built-in OpenTelemetry for distributed tracing and metrics.

📦 Installation

Prerequisites: Local Installation

For local development, install the server globally using npm link:

# From the ibmi-mcp-server directory
npm install
npm run build
npm link

This makes the ibmi-mcp-server command available globally on your machine. After linking, you can use npx ibmi-mcp-server in any client configuration.

Note: TOOLS_YAML_PATH must be an absolute path to your tools configuration directory (e.g., /full/path/to/prebuiltconfigs).

Remote Server Setup

For HTTP remote connections, you need to:

1. Start the server with IBM i authentication enabled:

# Ensure your .env has these settings:
MCP_AUTH_MODE=ibmi
IBMI_HTTP_AUTH_ENABLED=true
IBMI_AUTH_ALLOW_HTTP=true  # For development only!

npm run start:http

2. Obtain an access token:

# Use the token script to authenticate
node get-access-token.js --verbose

# Or set it directly in your environment
export IBMI_MCP_ACCESS_TOKEN="your-token-here"

See IBM i HTTP Authentication for detailed authentication setup. 3. Configure your client with the server URL and Bearer token (examples below).

⚠️ Production Note: Replace http://localhost:3010 with your production endpoint URL and ensure HTTPS is enabled (IBMI_AUTH_ALLOW_HTTP=false).

Client Configurations

# Add local stdio server
claude mcp add ibmi-mcp \
  --env DB2i_HOST=your-ibmi-host.com \
  --env DB2i_USER=your-username \
  --env DB2i_PASS=your-password \
  --env DB2i_PORT=8076 \
  --env MCP_TRANSPORT_TYPE=stdio \
  -- npx ibmi-mcp-server --tools /absolute/path/to/prebuiltconfigs

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio",
        "NODE_OPTIONS": "--no-deprecation"
      }
    }
  }
}

# Add remote HTTP server with authentication
claude mcp add --transport http ibmi-mcp http://localhost:3010/mcp \
  --header "Authorization: Bearer YOUR_ACCESS_TOKEN_HERE"

{
  "mcpServers": {
    "ibmi-mcp": {
      "url": "http://localhost:3010/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "${IBMI_TOOLS_PATH}"],
      "env": {
        "DB2i_HOST": "${DB2i_HOST}",
        "DB2i_USER": "${DB2i_USER}",
        "DB2i_PASS": "${DB2i_PASS}",
        "DB2i_PORT": "${DB2i_PORT:-8076}",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

# List configured servers
claude mcp list

# Get server details
claude mcp get ibmi-mcp

# Remove a server
claude mcp remove ibmi-mcp

# Check server status in Claude Code
/mcp

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "url": "http://localhost:3010/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

# Add local stdio server
code --add-mcp '{
  "name": "ibmiMcp",
  "type": "stdio",
  "command": "npx",
  "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
  "env": {
    "DB2i_HOST": "your-ibmi-host.com",
    "DB2i_USER": "your-username",
    "DB2i_PASS": "your-password",
    "DB2i_PORT": "8076",
    "MCP_TRANSPORT_TYPE": "stdio"
  }
}'

{
  "servers": {
    "ibmiMcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

# Add remote HTTP server
code --add-mcp '{
  "name": "ibmiMcp",
  "type": "http",
  "url": "http://localhost:3010/mcp",
  "headers": {
    "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
  }
}'

{
  "servers": {
    "ibmiMcp": {
      "type": "http",
      "url": "http://localhost:3010/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

{
  "inputs": [
    {
      "id": "db2iHost",
      "type": "promptString",
      "description": "IBM i DB2 host address"
    },
    {
      "id": "db2iUser",
      "type": "promptString",
      "description": "IBM i username"
    },
    {
      "id": "db2iPass",
      "type": "promptString",
      "description": "IBM i password",
      "password": true
    }
  ],
  "servers": {
    "ibmiMcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "${input:db2iHost}",
        "DB2i_USER": "${input:db2iUser}",
        "DB2i_PASS": "${input:db2iPass}",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "url": "http://localhost:3010/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "url": "http://localhost:3010/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "url": "http://localhost:3010/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio",
        "NODE_OPTIONS": "--no-deprecation"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "url": "http://localhost:3010/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ibmi-mcp": {
      "type": "local",
      "enabled": true,
      "command": ["npx", "ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "environment": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      },
      "enabled": true
    }
  }
}

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ibmi-mcp": {
      "type": "remote",
      "enabled": true,
      "url": "http://localhost:3010/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "url": "http://localhost:3010/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "command": "npx",
      "args": ["ibmi-mcp-server", "--tools", "/absolute/path/to/prebuiltconfigs"],
      "env": {
        "DB2i_HOST": "your-ibmi-host.com",
        "DB2i_USER": "your-username",
        "DB2i_PASS": "your-password",
        "DB2i_PORT": "8076",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

{
  "mcpServers": {
    "ibmi-mcp": {
      "url": "http://localhost:3010/mcp",
      "type": "streamableHttp",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN_HERE"
      }
    }
  }
}

import asyncio
import os
from agno.agent import Agent
from agno.tools.mcp import MCPTools, StreamableHTTPClientParams

# Get access token from environment
token = os.environ.get('IBMI_MCP_ACCESS_TOKEN')
if not token:
    raise ValueError("IBMI_MCP_ACCESS_TOKEN not set")

url = "http://localhost:3010/mcp"
server_params = StreamableHTTPClientParams(
    url=url,
    headers={"Authorization": f"Bearer {token}"}
)

async def main():
    async with MCPTools(
        url=url,
        server_params=server_params,
        transport="streamable-http"
    ) as tools:
        # List available tools
        result = await tools.session.list_tools()
        print(f"Available tools: {[t.name for t in result.tools]}")

        # Create agent
        agent = Agent(
            model="openai:gpt-4o",  # or your preferred model
            tools=[tools],
            name="ibmi-agent",
            show_tool_calls=True
        )

        # Run query
        await agent.aprint_response("What is the system status?")

if __name__ == "__main__":
    asyncio.run(main())

import asyncio
import os
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    token = os.environ.get('IBMI_MCP_ACCESS_TOKEN')
    if not token:
        raise ValueError("IBMI_MCP_ACCESS_TOKEN not set")

    headers = {"Authorization": f"Bearer {token}"}

    async with streamablehttp_client(
        "http://localhost:3010/mcp",
        headers=headers
    ) as (read_stream, write_stream, _):
        async with ClientSession(read_stream, write_stream) as session:
            await session.initialize()

            # List tools
            tools = await session.list_tools()
            print(f"Tools: {[t.name for t in tools.tools]}")

            # Execute a tool
            result = await session.call_tool("system_status", {})
            print(result)

if __name__ == "__main__":
    asyncio.run(main())

Troubleshooting

Connection Issues:

• Verify npm link was successful: which ibmi-mcp-server
• Check that TOOLS_YAML_PATH is an absolute path
• Ensure IBM i credentials are correct

Authentication Failures (Remote):

• Confirm server is running with IBMI_HTTP_AUTH_ENABLED=true
• Verify token is valid: echo $IBMI_MCP_ACCESS_TOKEN
• Check server logs for authentication errors

Tool Loading Errors:

• Validate YAML configuration: npm run validate -- --config prebuiltconfigs
• Check file permissions on tools directory
• Review server startup logs for parsing errors

🤖 IBM i Agents

IBM i Agents are specialized components designed to interact with the IBM i system, providing capabilities such as monitoring, management, and automation.

Key Features

• Integration with IBM i: Seamless integration with IBM i system APIs and tools.
• Modular Architecture: Easily extendable and customizable to fit specific use cases.
• Real-time Monitoring: Continuous monitoring of system performance and health.

Getting Started

Navigate to the agents directory and follow the setup instructions in the README. This includes details on configuration, running agents, and examples. Most agent examples require the MCP server to be running in HTTP mode. Read the docs for each agent example for details.

⚙️ Configuration

Configure the server using these environment variables (or a .env file):

To set the server environment variables, create a .env file in the root of this project:

cp .env.example .env
code .env

Then edit the .env file with your IBM i connection details.

🔐 IBM i HTTP Authentication (Beta)

The server supports IBM i HTTP authentication that allows clients to obtain access tokens for authenticated SQL tool execution. This enables per-user connection pooling and secure access to IBM i resources.

Authentication Flow

1. Client Authentication: Clients authenticate with IBM i credentials via HTTP Basic Auth
2. Token Generation: Server creates a secure Bearer token and establishes a dedicated connection pool
3. Tool Execution: Subsequent tool calls use the Bearer token for authenticated execution
4. Pool Management: Each token maintains its own connection pool for isolation and security

Configuration

To enable IBM i HTTP authentication, we need to set up Encryption keys and configure the server environment. To protect IBM i credentials during transmission, the authentication flow uses RSA and AES encryption. You need to generate an RSA keypair for the server:

mkdir -p secrets
openssl genpkey -algorithm RSA -out secrets/private.pem -pkeyopt rsa_keygen_bits:2048
openssl rsa -pubout -in secrets/private.pem -out secrets/public.pem

Create or update your .env file with the following settings:

# Enable IBM i authentication system
IBMI_HTTP_AUTH_ENABLED=true
MCP_AUTH_MODE=ibmi

# IBM i authentication settings
IBMI_AUTH_KEY_ID=development
IBMI_AUTH_PRIVATE_KEY_PATH=secrets/private.pem
IBMI_AUTH_PUBLIC_KEY_PATH=secrets/public.pem

# Security settings
IBMI_AUTH_ALLOW_HTTP=true          # Development only - use HTTPS in production
IBMI_AUTH_TOKEN_EXPIRY_SECONDS=3600 # Token lifetime (1 hour)

# Resource management
IBMI_AUTH_MAX_CONCURRENT_SESSIONS=100
IBMI_AUTH_CLEANUP_INTERVAL_SECONDS=300

# IBM i connection details
DB2i_HOST=your-ibmi-host
DB2i_USER=your-username
DB2i_PASS=your-password

Getting Access Tokens

Option 1: Using the Token Script (Recommended)

Use the included get-access-token.js script to obtain authentication tokens:

# Using credentials from .env file
node get-access-token.js --verbose

# Using CLI arguments (overrides .env)
node get-access-token.js --user myuser --password mypass --host my-ibmi-host

# Quiet mode for shell evaluation
eval $(node get-access-token.js --quiet)
echo $IBMI_MCP_ACCESS_TOKEN

The script automatically:

• Loads IBM i credentials from .env with CLI fallback
• Fetches the server's public key
• Encrypts credentials client-side
• Requests an access token
• Sets IBMI_MCP_ACCESS_TOKEN environment variable
• Provides copy-paste export commands

Sequence Overview

sequenceDiagram
    participant CLI as Client CLI
    participant Auth as MCP Server (/api/v1/auth)
    participant IBM as IBM i

    CLI->>Auth: GET /api/v1/auth/public-key
    Auth-->>CLI: { keyId, publicKey }

    CLI->>CLI: Generate AES-256-GCM session key + IV
    CLI->>CLI: Encrypt credentials + request body with session key
    CLI->>CLI: Encrypt session key with server public key (RSA-OAEP)

    CLI->>Auth: POST /api/v1/auth { keyId, encryptedSessionKey, iv, authTag, ciphertext }
    Auth->>Auth: Look up keyId, decrypt session key with private key
    Auth->>Auth: Decrypt ciphertext, validate GCM tag, validate payload

    Auth->>IBM: Authenticate against IBM i with decrypted credentials
    IBM-->>Auth: Success/Failure

    Auth->>Auth: Generate access token, provision pool session
    Auth-->>CLI: 201 JSON { access_token, expires_in, ... }

Client Integration

Once you have a token, use it in your MCP client to authenticate requests:

import asyncio
import os
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    # Get the access token from environment
    token = os.environ.get('IBMI_MCP_ACCESS_TOKEN')
    if not token:
        raise ValueError("IBMI_MCP_ACCESS_TOKEN environment variable not set")

    # Set up authentication headers
    headers = {"Authorization": f"Bearer {token}"}

    # Connect to the IBM i MCP server with authentication
    async with streamablehttp_client(
        "http://localhost:3010/mcp",
        headers=headers
    ) as (read_stream, write_stream, _):
        # Create a session using the authenticated streams
        async with ClientSession(read_stream, write_stream) as session:
            # Initialize the connection
            await session.initialize()

            # List available tools (now authenticated with your IBM i credentials)
            tools = await session.list_tools()
            print(f"Available tools: {[tool.name for tool in tools.tools]}")

            # Execute a tool with authenticated IBM i access
            result = await session.call_tool("system_status", {})
            print(f"System status result: {result}")

if __name__ == "__main__":
    asyncio.run(main())

Security Considerations

Development Environment:

• IBMI_AUTH_ALLOW_HTTP=true allows HTTP for testing
• Use localhost/trusted networks only
• Shorter token lifetimes for testing

Production Environment:

• IBMI_AUTH_ALLOW_HTTP=false enforces HTTPS
• Use proper TLS certificates
• Longer token lifetimes for stability
• Network security and access controls
• Monitor IBMI_AUTH_MAX_CONCURRENT_SESSIONS for resource usage

Authentication Endpoints

When enabled (IBMI_HTTP_AUTH_ENABLED=true), the server provides these endpoints:

🧩 SQL Tool Configuration

The Primary way to confgure tools used by this MCP server is through tools.yaml files (see prebuiltconfigs/ for examples). There are 3 main sections to each yaml file: sources, tools, and toolsets. Below is a breakdown of each section

Sources

The sources section of your tools.yaml defines the data sources the MCP server has access to

sources:
  ibmi-system:
    host: ${DB2i_HOST}
    user: ${DB2i_USER}
    password: ${DB2i_PASS}
    port: 8076
    ignore-unauthorized: true

[!NOTE] The environment variables DB2i_HOST, DB2i_USER, DB2i_PASS, and DB2i_PORT can be set in the server .env file. see Configuration

Tools

The tools section of your tools.yaml defines the actions your agent can take: what kind of tool it is, which source(s) it affects, what parameters it uses, etc.

tools:
  system_status:
    source: ibmi-system
    description: "Overall system performance statistics with CPU, memory, and I/O metrics"
    parameters: []
    statement: |
      SELECT * FROM TABLE(QSYS2.SYSTEM_STATUS(RESET_STATISTICS=>'YES',DETAILED_INFO=>'ALL')) X

Toolsets

The toolsets section of your tools.yaml allows you to define groups of tools that you want to be able to load together. This can be useful for defining different sets for different agents or different applications.

toolsets:
  performance:
    tools:
      - system_status
      - system_activity
      - remote_connections
      - memory_pools
      - temp_storage_buckets
      - unnamed_temp_storage
      - http_server
      - system_values
      - collection_services
      - collection_categories
      - active_job_info

More documentation on SQL tools coming soon!

🚀 Running the Server (Development)

The server supports multiple transport modes and session configurations for different development scenarios. Use the appropriate startup command based on your needs.

Transport Modes

HTTP Transport (Recommended for Development)

# Basic HTTP server
npm run start:http

# HTTP with custom tools path
npm run start:http -- --tools ./my-configs

# HTTP with specific toolsets
npm run start:http -- --toolsets performance,monitoring

Stdio Transport (for CLI tools and MCP Inspector)

# Basic stdio transport
npm run start:stdio

# Stdio with custom tools path
npm run start:stdio -- --tools ./my-custom-tools

Session Modes (HTTP Only)

The MCP_SESSION_MODE environment variable controls how the HTTP server handles client sessions:

• auto (default): Automatically detects client capabilities and uses the best session mode
• stateful: Maintains persistent sessions with connection state
• stateless: Each request is independent, no session state maintained

# Set session mode via environment variable
MCP_SESSION_MODE=stateful npm run start:http

# Or set in .env file
echo "MCP_SESSION_MODE=stateful" >> .env
npm run start:http

CLI Options

Both transport modes support these command-line options:

Note: CLI arguments override corresponding settings in .env file when provided. | Option | Short | Description | Example | | -------------------- | ----- | ----------------------------------------------------------------------------- | --------------------------------- | | --tools <path> | | Override YAML tools configuration path (overrides TOOLS_YAML_PATH) | --tools ./custom-configs | | --toolsets <list> | -ts | Load only specific toolsets (comma-separated) (overrides SELECTED_TOOLSETS) | --toolsets performance,security | | --transport <type> | -t | Force transport type (http or stdio) (overrides MCP_TRANSPORT_TYPE) | --transport http | | --help | -h | Show help information | --help | | --list-toolsets | | List available toolsets from YAML configuration | --list-toolsets |

Common Development Scenarios

1. Standard Development Server

npm run start:http
# Server: http://localhost:3010/mcp
# Tools: prebuiltconfigs/ (from .env)
# Session: auto-detected

2. Custom Tools Path

npm run start:http -- --tools ./my-tools
# Server: http://localhost:3010/mcp (port from .env or default)
# Tools: ./my-tools

3. Specific Toolsets Only

npm run start:http -- --toolsets performance,monitoring
# Only loads tools from 'performance' and 'monitoring' toolsets

Development Tips

• Hot Reloading: Enable YAML_AUTO_RELOAD=true in .env for automatic tool configuration updates
• Verbose Logging: Set MCP_LOG_LEVEL=debug for detailed operation logs
• CORS: Configure MCP_ALLOWED_ORIGINS for web-based clients
• Authentication: Use MCP_AUTH_MODE=ibmi with IBM i HTTP auth for token-based access

Troubleshooting

Port Already in Use

# Configure port in .env file
echo "MCP_HTTP_PORT=3011" >> .env
npm run start:http

Tools Not Loading

# Check tools path
npm run start:http -- --tools ./prebuiltconfigs

# List available toolsets first
npm run start:http -- --list-toolsets --tools ./prebuiltconfigs

# Get help
npm run start:http -- --help

🕵️‍♂️ MCP Inspector

The MCP Inspector is a tool for exploring and debugging the MCP server's capabilities. It provides a user-friendly interface for interacting with the server, viewing available tools, and testing queries.

Here are the steps to run the MCP Inspector:

1. Make sure to build the server

cd ibmi-mcp-server/
npm run build

2. Create an mcp.json file:

cp template_mcp.json mcp.json

Fill out the connection details in mcp.json with your IBM i system information. You should use the same credentials as in your .env file:

{
  "mcpServers": {
    "default-server": {
      "command": "node",
      "args": ["dist/index.js"],
      "env": {
        "TOOLS_YAML_PATH": "prebuiltconfigs",
        "NODE_OPTIONS": "--no-deprecation",
        "DB2i_HOST": "<DB2i_HOST>",
        "DB2i_USER": "<DB2i_USER>",
        "DB2i_PASS": "<DB2i_PASS>",
        "DB2i_PORT": "<DB2i_PORT>",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

3. Start the MCP Inspector

npm run mcp-inspector

4. Click on the URL displayed in the terminal to open the MCP Inspector in your web browser.

Starting MCP inspector...
⚙️ Proxy server listening on 127.0.0.1:6277
🔑 Session token: EXAMPLE_TOKEN
Use this token to authenticate requests or set DANGEROUSLY_OMIT_AUTH=true to disable auth

🔗 Open inspector with token pre-filled:
  http://localhost:6274/?MCP_PROXY_AUTH_TOKEN=EXAMPLE_TOKEN

🔍 MCP Inspector is up and running at http://127.0.0.1:6274 🚀

5. Use the MCP Inspector to explore and test your MCP server's capabilities

• View available tools and their parameters
• Test queries against the server
• Debug issues with tool execution

🐳 Docker & Podman Deployment

The project includes a comprehensive docker-compose.yml that sets up the complete MCP gateway with the IBM i MCP Server. ContextForge MCP Gateway is a feature-rich gateway, proxy and MCP Registry that federates MCP and REST services - unifying discovery, auth, rate-limiting, observability, virtual servers, multi-transport protocols, and an optional Admin UI into one clean endpoint for your AI clients. Read more about it here.

Prerequisites

Choose one of the following container platforms:

Docker

• Docker Desktop (macOS/Windows): Download here
• Docker Engine (Linux): Installation guide

Podman (Alternative to Docker)

• Podman Desktop (macOS/Windows): Download here
• Podman CLI (Linux): Installation guide
• podman-compose: pip install podman-compose

Build MCP Gateway Image

The docker-compose.yml uses a local build of the MCP Gateway image. To build it, clone the MCP Gateway repository and build the image:

git clone https://github.com/IBM/mcp-context-forge.git
cd mcp-context-forge

# Build image using Docker
make docker-prod

# Or build image using Podman
make podman-prod

This will create a local image named localhost/mcpgateway/mcpgateway that the docker-compose.yml can use. More details on building the MCP Gateway image can be found in the MCP Gateway Docs.

Configure MCP environment

Create a .env file in the ibmi-mcp-server directory with your IBM i connection details:

cd ibmi-mcp-server/
cp .env.example .env
# Edit .env with your IBM i connection details
code .env

make sure to set the follow variables in your .env file:

# IBM i connection details
DB2i_HOST="your_host"
DB2i_USER="your_user"
DB2i_PASS="your_pass"

# MCP Auth mode
MCP_AUTH_MODE=ibmi

# IBM i HTTP authentication settings
IBMI_AUTH_KEY_ID=development
IBMI_AUTH_PRIVATE_KEY_PATH=secrets/private.pem
IBMI_AUTH_PUBLIC_KEY_PATH=secrets/public.pem

# Enable IBM i HTTP authentication endpoints (requires MCP_AUTH_MODE=ibmi)
IBMI_HTTP_AUTH_ENABLED=true

# Allow HTTP requests for authentication (development only, use HTTPS in production)
IBMI_AUTH_ALLOW_HTTP=true

Note: You need to generate an RSA keypair for the server if you haven't already done so. See the IBM i HTTP Authentication section for instructions. Once you have your .env file configured, you can start the complete stack using Docker or Podman.

Quick Start with Docker

1. Start the complete stack:

# Start all services in background
docker-compose up -d

# Or start specific services
docker-compose up -d gateway ibmi-mcp-server postgres redis

2. Verify services are running:

docker-compose ps

Quick Start with Podman

1. Start the complete stack:

# Start all services in background
podman compose up -d

# Or start specific services
podman compose up -d gateway ibmi-mcp-server postgres redis

2. Verify services are running:

podman compose ps

Container Architecture

The docker-compose setup includes these services:

🔧 Service Management

Start Services

# Docker
docker-compose up -d                    # Start all services
docker-compose up -d gateway            # Start specific service
docker-compose up --no-deps gateway     # Start without dependencies

# Podman
podman compose up -d                    # Start all services
podman compose up -d gateway            # Start specific service
podman compose up --no-deps gateway     # Start without dependencies

Stop Services

# Docker
docker-compose down                     # Stop all services
docker-compose stop gateway             # Stop specific service

# Podman
podman compose down                     # Stop all services
podman compose stop gateway             # Stop specific service

View Logs

# Docker
docker-compose logs -f gateway          # Follow gateway logs
docker-compose logs --tail=100 ibmi-mcp-server

# Podman
podman compose logs -f gateway          # Follow gateway logs
podman compose logs --tail=100 ibmi-mcp-server

Rebuild Services

# Docker
docker-compose build ibmi-mcp-server    # Rebuild specific service
docker-compose up --build -d            # Rebuild and restart all

# Podman
podman compose build ibmi-mcp-server    # Rebuild specific service
podman compose up --build -d            # Rebuild and restart all

MCP Gateway UI:

After the Containers are up and running, you can access the MCP Context Forge UI at http://localhost:4444 Enter the demo credentials:

• User: admin
• Password: changeme To Configure the IBM i MCP server is the admin ui, navigate to the "Gateways/MCP Servers" tab. and enter the mcp server endpoint:
• IBM i mcp server endpoint: http://ibmi-mcp-server:3010 Once the MCP server is connect, you can then manage the tools provided by the server:

Virtual Server Catalog Demo (Comming soon!!)

🏗️ Architecture Overview

This template is built on a set of architectural principles to ensure modularity, testability, and operational clarity.

• Core Server (src/mcp-server/server.ts): The central point where tools and resources are registered. It uses a ManagedMcpServer wrapper to provide enhanced introspection capabilities. It acts the same way as the native McpServer, but with additional features like introspection and enhanced error handling.
• Transports (src/mcp-server/transports/): The transport layer connects the core server to the outside world. It supports both stdio for direct process communication and a streamable Hono-based http server.
• "Logic Throws, Handler Catches": This is the immutable cornerstone of our error-handling strategy.
  • Core Logic (logic.ts): This layer is responsible for pure, self-contained business logic. It throws a structured McpError on any failure.
  • Handlers (registration.ts): This layer interfaces with the server, invokes the core logic, and catches any errors. It is the exclusive location where errors are processed and formatted into a final response.
• Structured, Traceable Operations: Every operation is traced from initiation to completion via a RequestContext that is passed through the entire call stack, ensuring comprehensive and structured logging.

Key Features

Project Structure

• src/mcp-server/: Contains the core MCP server, tools, resources, and transport handlers.
• src/config/: Handles loading and validation of environment variables.
• src/services/: Reusable modules for integrating with external services (DuckDB, OpenRouter).
• src/types-global/: Defines shared TypeScript interfaces and type definitions.
• src/utils/: Core utilities (logging, error handling, security, etc.).
• src/index.ts: The main entry point that initializes and starts the server.

Explore the full structure yourself: See the current file tree in docs/tree.md or generate it dynamically:

npm run tree

Extending the System

The template enforces a strict, modular pattern for adding new tools and resources, as mandated by the Architectural Standard. The echoTool (src/mcp-server/tools/echoTool/) serves as the canonical example.

The "Logic Throws, Handler Catches" Pattern

This is the cornerstone of the architecture:

1. logic.ts: This file contains the pure business logic.
   • It defines the Zod schemas for input and output, which serve as the single source of truth for the tool's data contract.
   • The core logic function is pure: it takes validated parameters and a request context, and either returns a result or throws a structured McpError.
   • It never contains try...catch blocks for formatting a final response.
2. registration.ts: This file is the "handler" that connects the logic to the MCP server.
   • It imports the schemas and logic function from logic.ts.
   • It calls server.registerTool(), providing the tool's metadata and the runtime handler.
   • The runtime handler always wraps the call to the logic function in a try...catch block. This is the only place where errors are caught, processed by the ErrorHandler, and formatted into a standardized error response. This pattern ensures that core logic remains decoupled, pure, and easily testable, while the registration layer handles all transport-level concerns, side effects, and response formatting.

📄 License

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