PluginBench
MCP Server
Stale
Apache-2.0

IBM Maximo MCP Server

io.github.markusvankempen/maximo-mcp-server

Connect AI assistants to IBM Maximo for API discovery, OSLC querying, and intelligent code generation.

What is the IBM Maximo MCP server?

The Maximo MCP Server is a Model Context Protocol server that connects AI assistants like Claude, Cursor, and VS Code Copilot directly to IBM Maximo environments. It enables AI to discover APIs, inspect schemas, query live data via OSLC, generate UI code, and perform CRUD operations on Maximo records without manual API documentation.

This server bridges AI assistants and IBM Maximo by exposing 9 tools for schema discovery, live data querying, code generation, and record management. Instead of manually copying API docs, AI can inspect Object Structures, execute OSLC queries, generate Carbon Design tables, and create or update Maximo records. It's ideal for accelerating Maximo development, building dashboards, and automating workflows through natural language.

How to install IBM Maximo

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • MAXIMO_URL
    required

    Base URL for the Maximo REST API (e.g., https://your-host/maximo/api)

  • MAXIMO_API_KEY
    required
    secret

    API Key for Maximo authentication

  • MAXIMO_HOST

    Base Host URL for the Maximo instance

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "maximo-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "maximo-mcp-server"
      ],
      "env": {
        "MAXIMO_URL": "<YOUR_MAXIMO_URL>",
        "MAXIMO_API_KEY": "<YOUR_MAXIMO_API_KEY>",
        "MAXIMO_HOST": "<YOUR_MAXIMO_HOST>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • list_object_structures — List available Maximo Object Structures (APIs)
  • get_schema_details — Get field definitions for an Object Structure
  • query_maximo — Execute OSLC REST queries
  • render_carbon_table — Generate Carbon Design HTML tables
  • render_carbon_details — Generate detail view for a record
  • get_instance_details — Check server connectivity
  • create_record — Create a new record in any Maximo Object Structure
  • update_record — Partially update fields on an existing record by ID
  • run_action — Execute Maximo business actions (status changes, approvals)

Use cases

  • Generate OSLC API calls and REST queries for Maximo data retrieval
  • Build Python, JavaScript, or SQL scripts to export and analyze Maximo records
  • Create complete web dashboards and applications with Carbon Design System components
  • Create and update Maximo records (Work Orders, Assets, Service Requests) via natural language
  • Execute Maximo business workflows and status changes through AI-driven automation

IBM Maximo MCP server FAQ

What is the Maximo MCP Server?

It's a Model Context Protocol server that connects AI assistants (Claude, Cursor, VS Code Copilot) to IBM Maximo. It exposes 9 tools for API discovery, schema inspection, OSLC querying, code generation, and CRUD operations on Maximo records.

Is it free?

Yes. The server is open-source under Apache 2.0 license. You need a Maximo instance and API key to use it.

How do I install it in Cursor or Claude?

Install via npm (npx maximo-mcp-server) and configure your IDE's MCP settings with your Maximo URL and API key. For Cursor/Claude Desktop, add the server to your mcp.json config file with environment variables.

What authentication is required?

You need a Maximo API key with read access (or read+write for CRUD operations). Set MAXIMO_URL, MAXIMO_API_KEY, and MAXIMO_HOST in your .env file or IDE configuration.

Can I create and update records?

Yes. The server includes write tools (create_record, update_record, run_action) to create Work Orders, Assets, and other records, and to execute business workflows. Use a read-only key for exploration; enable write access only for known workflows.

Do I need the OpenAPI schema file?

No, but it's recommended. Downloading maximo_openapi.json from your Maximo instance enables offline schema lookups for faster AI responses. Without it, the server queries Maximo live for schema details.

README (reference)

Source of truth, from the repository.

<div align="center">

🏭 Maximo MCP Server

AI-Powered Development for IBM Maximo

Node.js MCP Maximo License Version

Transform your Maximo development workflow with AI-driven schema discovery, live data querying, intelligent code generation, and full write-back capabilities.

Author: Markus van Kempen
Email: mvankempen@ca.ibm.com | markus.van.kempen@gmail.com
Date: 16 September 2026

Getting Started • Documentation • Live Demo • Use Cases

</div>

🎯 What is This?

The Maximo MCP Server is a Model Context Protocol server that connects AI assistants (like Antigravity, Cursor, or VS Code Copilot) directly to your IBM Maximo environment. Instead of manually copying API documentation, the AI can:

CapabilityDescription
🔍 Discover APIsFind available Object Structures (MXWO, MXASSET, etc.)
📋 Inspect SchemasGet exact field names, types, and descriptions
📊 Query Live DataExecute OSLC REST queries and see real results
🎨 Generate UICreate Carbon Design System tables and dashboards
✅ Validate InstantlyTest queries before generating final code
✏️ Create RecordsCreate Work Orders, Assets, Service Requests via AI
🔄 Update RecordsPartially update any Maximo record by ID
⚡ Run ActionsTrigger Maximo business workflows (status changes, approvals)

📚 Documentation

Core Guides

DocumentDescription
📖 Maximo MCP Server GuideComplete setup, configuration, and tool reference
🔌 Maximo API Interaction GuideOSLC query syntax, code generation patterns, troubleshooting
🎬 Asset Manager Case StudyStep-by-step walkthrough of building a complete app
🧩 Maximo API Explorer GuideVS Code extension: install, connect, explore, generate apps

French Translations

DocumentDescription
📖 Guide du Serveur MCP MaximoVersion française du guide complet
🔌 Guide d'Interaction API MaximoVersion française du guide API

Word Documents

All guides are also available in .docx format in the docs/ folder for offline reading and sharing.


⚡ Quick Start

Prerequisites

  • Node.js v18 or higher
  • Maximo API Key with read access
  • AI IDE with MCP support (Antigravity, Cursor, VS Code + Continue)

Installation

Installation

Method 1: Run directly with npx (Recommended)

npx maximo-mcp-server

Method 2: Clone from Source

# Clone the repository
git clone https://github.com/markusvankempen/maximo-mcp-ai-integration-options.git
cd maximo-mcp-ai-integration-options

# Install dependencies
npm install

# Set up environment variables
cp .env.example .env
# Edit .env with your Maximo credentials

Environment Configuration

Edit the .env file with your Maximo credentials:

# .env (never commit this file!)
MAXIMO_URL=https://your-maximo-host.com/maximo/api
MAXIMO_HOST=https://your-maximo-host.com
MAXIMO_API_KEY=your-api-key-here
MAXIMO_OPENAPI_PATH=./maximo_openapi.json
PORT=3002

Download the OpenAPI Schema (Recommended)

The OpenAPI schema file enables offline schema lookups for faster AI responses:

# Download from your Maximo instance
curl -X GET "https://your-maximo-host.com/maximo/oslc/oas/api" \
     -H "apikey:your-api-key-here" \
     -o maximo_openapi.json

Alternatively, download via Swagger UI at: https://your-host/maximo/oslc/oas/api.html (Click "Explore" or "Download")

Method 3: Direct Browser Download (Manual)

If curl fails (e.g., due to SSL/network errors), you can manually download the file:

  1. Open this URL in your browser: https://[YOUR_MAXIMO_HOST]/maximo/oslc/oas/api (Replace [YOUR_MAXIMO_HOST] with your actual server address)

  2. You may be prompted to log in to Maximo.

  3. Once the JSON loads, right-click the page and select "Save Page As...".

  4. Save the file as maximo_openapi.json in your project root folder.

Note: This file is ~12MB and contains all Object Structure definitions for your Maximo instance.

IDE Configuration

VS Code with GitHub Copilot (Recommended)

Option 1: Install from the MCP Server Gallery

  1. Enable chat.mcp.gallery.enabled in VS Code settings
  2. Open the Extensions view (⇧⌘X)
  3. Type @mcp maximo in the search field
  4. Click Install to add the Maximo MCP server

Option 2: Add manually via mcp.json

  1. Open the Command Palette (⇧⌘P) → MCP: Open Workspace Folder Configuration
  2. Add the following configuration:
{
  "inputs": [
    {
      "type": "promptString",
      "id": "maximo-url",
      "description": "Maximo REST API Base URL (e.g., https://your-host/maximo/api)"
    },
    {
      "type": "promptString",
      "id": "maximo-api-key",
      "description": "Maximo API Key",
      "password": true
    },
    {
      "type": "promptString",
      "id": "maximo-host",
      "description": "Maximo Host URL (e.g., https://your-host)"
    }
  ],
  "servers": {
    "maximo-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "maximo-mcp-server"],
      "env": {
        "MAXIMO_URL": "${input:maximo-url}",
        "MAXIMO_API_KEY": "${input:maximo-api-key}",
        "MAXIMO_HOST": "${input:maximo-host}"
      }
    }
  }
}
  1. VS Code will prompt you for your Maximo credentials when the server starts.

💡 Tip: This project includes a .vscode/mcp.json file. If you clone the repo, VS Code will auto-detect the MCP server configuration.

Google Antigravity (Manual Setup Required)

⚠️ Note: The Antigravity MCP Store is curated and does not auto-discover servers from the registry. You must add this server manually.

  1. Open Antigravity
  2. Click "..." dropdown at the top of the Agent panel
  3. Select "MCP Servers" → "Manage MCP Servers" → "View raw config"
  4. Add to your mcp_config.json:
{
  "mcpServers": {
    "maximo-mcp-server": {
      "command": "npx",
      "args": ["-y", "maximo-mcp-server"],
      "env": {
        "MAXIMO_URL": "https://your-maximo-host/maximo/api",
        "MAXIMO_API_KEY": "your-api-key-here",
        "MAXIMO_HOST": "https://your-maximo-host"
      }
    }
  }
}
  1. Save and click Refresh

Cursor / Claude Desktop

# Copy the template
cp config/mcp_config.json.example ~/.cursor/mcp.json
# Or for Claude Desktop:
cp config/mcp_config.json.example ~/Library/Application\ Support/Claude/claude_desktop_config.json

Edit with your Maximo credentials:

{
  "mcpServers": {
    "maximo-mcp-server": {
      "command": "npx",
      "args": ["-y", "maximo-mcp-server"],
      "env": {
        "MAXIMO_URL": "https://your-maximo-host/maximo/api",
        "MAXIMO_API_KEY": "your-api-key-here"
      }
    }
  }
}

Verify Connection

In your AI IDE, ask:

"Is the Maximo MCP server connected?"

The AI will call get_instance_details and confirm connectivity.


🎬 Live Demo

Asset Manager Application

We built a complete Maximo Asset Manager web application using only natural language prompts and the MCP server.

<div align="center">

Asset Manager Dashboard

50 assets loaded with real-time filtering and search

</div>

Demo Features

FeatureScreenshot
Full Dashboard50 assets, 4 stat cards, 3 sites
Search FilterPump Search
Site FilterLAREDO Filter

🎥 Screen Recording

A complete video demonstration is available: assets_demo_recording.webp

Try It Yourself

# Start the local proxy server
node server.js

# Open in browser
open http://localhost:3002/demos/assets.html

🛠 Available MCP Tools

The server exposes 9 tools to the AI — 6 read tools and 3 write/CRUD tools:

MCP Tools UI

Read Tools

Tool NameDescription
list_object_structuresList available Maximo Object Structures (APIs)
get_schema_detailsGet field definitions for an Object Structure
query_maximoExecute OSLC REST queries
render_carbon_tableGenerate Carbon Design HTML tables
render_carbon_detailsGenerate detail view for a record
get_instance_detailsCheck server connectivity

Write Tools (CRUD)

⚠️ Write tools modify live data. Use a read-only API key for exploration; only enable write access for known workflows.

Tool NameDescription
create_recordCreate a new record in any Maximo Object Structure
update_recordPartially update fields on an existing record by ID
run_actionExecute Maximo business actions (status changes, approvals)

💡 Use Cases

1. Generate API Calls

"Get me the last 10 approved work orders from BEDFORD site"

The AI calls get_schema_details(MXWO), understands the fields, and generates:

GET /maximo/api/os/mxwo
    ?oslc.where=status="APPR" and siteid="BEDFORD"
    &oslc.select=wonum,description,status,reportdate
    &oslc.orderBy=-reportdate
    &oslc.pageSize=10
    &lean=1

2. Generate Python Scripts

"Write a Python script to export all Priority 1 work orders to CSV"

import requests
import csv

response = requests.get(
    "https://your-host/maximo/api/os/mxwo",
    params={"oslc.where": "wopriority=1", "lean": 1},
    headers={"apikey": "YOUR_KEY"}
)

with open("priority1_workorders.csv", "w") as f:
    writer = csv.DictWriter(f, fieldnames=["wonum", "description"])
    writer.writeheader()
    writer.writerows(response.json()["member"])

3. Generate SQL Queries

"Write SQL to find overdue work orders"

SELECT wonum, description, status, targcompdate
FROM workorder
WHERE status NOT IN ('COMP', 'CLOSE', 'CAN')
  AND targcompdate < CURRENT_DATE;

4. Build Complete Applications

"Create an HTML dashboard to display assets"

Result: A complete web application with:

  • Dark theme with glassmorphism
  • Search and filter functionality
  • Interactive detail panels
  • Pre-loaded data from Maximo

See the Asset Manager Case Study for the full walkthrough.

5. Create & Update Records (CRUD)

"Create a corrective maintenance work order for the BEDFORD site, priority 1, description 'Pump failure inspection'."

The AI calls get_schema_details(MXWO) to confirm field names, then create_record:

POST /maximo/api/os/MXWO?lean=1
apikey: YOUR_KEY
Content-Type: application/json

{ "description": "Pump failure inspection", "siteid": "BEDFORD", "worktype": "CM", "wopriority": 1 }

"Now approve work order 1025 with memo 'Reviewed and approved'."

POST /maximo/api/os/MXWO/1025?action=changeStatus&lean=1
apikey: YOUR_KEY
Content-Type: application/json

{ "status": "APPR", "memo": "Reviewed and approved" }

See the full guide: Maximo MCP Server Guide — CRUD Workflows


🧩 VS Code Extensions

This project includes two VS Code extensions for interactive Maximo API development — no AI agent required.

Maximo API Explorer

A full-featured VS Code extension for discovering, testing, and generating code for Maximo REST APIs.

Maximo API Explorer — Sidebar

Connected to a live Maximo instance showing Object Structures (MXWO, MXSR, MXASSET, etc.) and API Endpoints.

FeatureDescription
Sidebar Tree ViewBrowse all Object Structures (MXWO, MXASSET, MXSR, etc.) with attributes, types, and relationships
Interactive API TesterBuild OSLC queries visually, send raw requests, inspect schemas — all in a WebView panel
Code Snippet GeneratorGenerate ready-to-use API calls in cURL, Python, JavaScript, TypeScript, and Java
Carbon App GeneratorScaffold complete Work Order Browser and Asset Manager web apps with one click
Export for AI AgentsExport schemas and docs to .maximo/ for use with Copilot, Cursor, or any AI assistant

Maximo API Explorer — API Tester

OSLC Query Builder with live JSON response (200 OK, 20 records from MXWO).

Quick Start

cd maximo-api-explorer
npm install && npm run compile
# Press F5 in VS Code to launch the Extension Development Host

See the full guide: Maximo API Explorer Guide

Maximo Cursor Explorer

A fork of the API Explorer optimized for Cursor's AI features:

FeatureDescription
.cursorrules GeneratorAuto-generate rules giving Cursor AI deep Maximo API knowledge
AI Context ExportExport schemas to .cursor/context/ for use with @file references
Prompt TemplatesPre-built prompts for OSLC queries, CRUD services, dashboards, and more
All Standard FeaturesEverything from the API Explorer, plus a dedicated Cursor AI tab
cd maximo-cursor-extension
npm install && npm run compile
# Press F5 in VS Code to launch

📁 Project Structure

Maximo-MCP/
├── maximo-mcp-server.js       # 🔌 MCP Server implementation
├── server.js                  # 🌐 Local proxy server for CORS
├── package.json               # 📦 Dependencies & scripts
├── README.md                  # This file
├── .env.example               # Environment template
│
├── docs/                      # 📚 Documentation
│   ├── Maximo_MCP_Server_Guide.md         # Complete MCP guide
│   ├── Maximo_API_Interaction_Guide.md    # API interaction patterns
│   ├── Asset_Manager_App_Case_Study.md    # Build walkthrough
│   ├── Maximo_API_Explorer_Guide.md       # VS Code extension guide
│   ├── Maximo_MCP_Server_Guide_FR.md      # French translation
│   └── Maximo_API_Interaction_Guide_FR.md # French translation
│
├── maximo-api-explorer/       # 🧩 VS Code Extension
│   ├── package.json                       # Extension manifest
│   ├── src/extension.ts                   # Activation & commands
│   ├── src/api/                           # API client & discovery
│   ├── src/auth/                          # Authentication manager
│   ├── src/views/                         # Sidebar tree & WebView panel
│   ├── src/snippets/                      # Multi-language code generator
│   ├── src/templates/                     # Carbon app generators
│   └── src/export/                        # AI context exporter
│
├── maximo-cursor-extension/   # 🤖 Cursor-Optimized Extension
│   ├── package.json                       # Extension manifest
│   ├── src/extension.ts                   # Activation & commands
│   ├── src/cursor/                        # .cursorrules, prompts, context
│   └── src/...                            # Same structure as api-explorer
│
├── CodeExample/               # 📦 Standalone Carbon App Example
│   └── maximo-workorders-carbon/          # Work Order Browser (reference)
│
├── demos/                     # 🎨 Demo Applications
│   ├── assets.html                        # Asset Manager app
│   ├── carbon_workorders.html             # Carbon table demo
│   └── index.html                         # API visualization demo
│
├── images/                    # 📸 Screenshots & Recordings
│   ├── assets_demo_recording.webp         # Full demo recording
│   ├── assets_loaded.png                  # Dashboard screenshot
│   ├── api-explorer-sidebar.png           # Extension sidebar & tree view
│   ├── api-explorer-tester.png            # OSLC Query Builder & JSON response
│   ├── api-explorer-carbon-app.png        # Generated Work Order Browser app
│   ├── api-explorer-snippets.png          # Carbon App Templates (Examples tab)
│   └── ...                                # More screenshots
│
└── config/                    # ⚙️ Configuration Templates
    └── mcp_config.json.example            # MCP config template

🔒 Security Best Practices

PracticeDescription
🔐 Local ExecutionMCP server runs on your machine; API keys never leave your environment
📖 Read-Only Keys for DevUse limited-permission API keys for exploration and development
✏️ Separate Write KeysOnly enable write permissions on API keys used for known CRUD workflows
🔒 Environment VariablesNever hardcode credentials in config files
🌐 HTTPS OnlyAlways use encrypted connections to Maximo
🧪 Test Non-Production FirstAlways validate CRUD operations on a dev/test instance before production

🤝 Contributing

Contributions are welcome! Please read our contributing guidelines before submitting PRs.

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

📄 License

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


🙏 Acknowledgments

Related MCP servers

MCP server demo — tickets, schema discovery, auth, and PII gating. stdio + HTTP.

1
HTML
View repository →

IBM Quantum OpenQASM 2.0 MCP — list backends, submit QASM, poll jobs, get histograms.

0
Shell
Apache-2.0
View repository →

Lifts WxO Slack limits: every-message wake-up, multi-channel MCP. https://markusvankempen.github.io/

0
Shell
Apache-2.0
View repository →
WXWxO Agent MCP logo

WxO Agent MCP

Maintained

Invoke a Watson Orchestrate agent via MCP. Configure with WO_AGENT_ID.

0
View repository →
WAWatson Orchestrate logo

Manage IBM Watson Orchestrate tools, agents, connections from Cursor, Copilot, Claude.

0
View repository →
ZEZendesk MCP logo

Zendesk MCP

Maintained

Zendesk MCP: 14 tools for AI agents — create, search, assign, comment, and close support tickets.

0
JavaScript
Apache-2.0
View repository →