MAS 9.2 New Features: What Changed Since 9.1

IBM Maximo Application Suite 9.2, released in June 2026, is the second major release in the 9.x line and the most feature-rich update the platform has seen since the architectural shift from Maximo 7.6. Where MAS 9.1 laid the foundation with role-based applications, embedded AI, and the Maximo Application Framework, MAS 9.2 builds on that foundation with agentic AI workflows, a Model Context Protocol (MCP) Server for external agent integration, expanded safety and compliance capabilities, new industry solutions, and significant technical platform improvements.

For organizations currently on MAS 9.1, 9.0, or the 8.x Extended Support releases, this article covers every major change in MAS 9.2, what it means for your environment, and how to plan your upgrade. For those still on Maximo 7.6, the direct upgrade path to 9.2 is now the most compelling reason to move, as the gap between the legacy platform and the current suite has never been wider. We will walk through the agentic AI layer, the MCP Server, the new HSE workflows, industry solution updates, technical platform changes, and a practical upgrade plan.

Agentic AI Workflows: From Insights to Actions

The headline feature of MAS 9.2 is the introduction of agentic AI workflows. In MAS 9.0 and 9.1, AI was primarily assistive: the Maximo Assistant answered questions, Work Order Intelligence classified work orders, and similar record detection helped users find related items. These were useful capabilities, but they stopped at providing information. A human still had to take every action.

MAS 9.2 takes a step further by introducing agentic workflows that can guide decisions and, in configured scenarios, take actions on behalf of users. The distinction between assistive AI and agentic AI is important. Assistive AI says, "Here is what I found." Agentic AI says, "Here is what I found, here is what I recommend, and here is the action I can take if you approve." The system does not operate autonomously without human oversight, but it reduces the friction between insight and execution by packaging the recommendation and the action together.

Maximo Condition Insight is the flagship agentic capability in this release. Introduced in late 2025 within the APM stack, Condition Insight brings together work orders, inspections, meter readings, and reliability strategies to identify patterns in asset behavior. In MAS 9.2, it has matured to the point where it can recommend specific corrective actions in natural language. For example, if a pump shows increasing vibration trends combined with a history of bearing failures, Condition Insight does not just flag the anomaly. It generates a recommendation: "Vibration on pump P-301 has increased 40% over the past 14 days. The asset has failed three times in the past 18 months due to bearing wear. Recommend scheduling a vibration analysis within 7 days and ordering replacement bearing kit BK-4471."

The agentic layer extends to scheduling as well. Conversational scheduling, introduced in 9.2, allows planners and field service managers to explore what-if scenarios using natural language. A scheduler can ask, "What if I add two technicians to the afternoon shift next Tuesday?" or "What happens if I prioritize the boiler inspection at Plant 2 over the scheduled PMs?" The system applies the organization's constraints, technician availability, skill qualifications, travel time, and work order priority to return optimized assignment options. This replaces the manual process of adjusting assignments, running calculations, and reverting changes that has dominated scheduling workflows for years.

The Maximo Assistant has also been enhanced in 9.2. On the desktop, the assistant now supports more complex analytical queries. A user can ask, "What is the average time to complete corrective work orders on assets in the northern plant over the past six months?" and the assistant will query the database, perform the calculation, and present the result in a formatted response with a chart. On mobile, the assistant helps technicians find asset information and review work order history using natural language, which compresses the time spent searching for context before starting a job.

The practical implication for upgrade planning is that agentic AI requires the AI Service to be deployed and configured. If your MAS 9.1 environment already has the AI Service running for the Maximo Assistant, the 9.2 upgrade will extend those capabilities automatically. If you have not yet deployed the AI Service, you will need to do so to take advantage of the agentic workflows. The AI Service runs as an additional pod in your OpenShift cluster and requires GPU resources for model inference. Plan your cluster sizing accordingly, and verify that your OpenShift cluster has sufficient GPU capacity before initiating the upgrade.

MCP Server: Bringing External Agents Into Maximo

One of the most architecturally significant additions in MAS 9.2 is the Model Context Protocol (MCP) Server. MCP is an open standard that allows AI agents and applications to communicate with external systems through a standardized interface. By implementing an MCP Server, IBM has made it possible for organizations to bring their own AI agents and integrate them directly with Maximo Manage APIs.

This is a bigger deal than it might sound. Since the rise of large language models and AI agents, organizations have been building custom AI tools for maintenance, operations, and reliability. These tools typically interact with Maximo through REST APIs, which works but requires custom integration code for each agent. The MCP Server standardizes this interaction. An external agent can discover available Maximo API operations, invoke them, and receive structured responses without custom integration work.

For example, an organization might have a custom AI agent that monitors weather patterns and predicts which assets are likely to be affected by approaching storms. With the MCP Server, that agent can query Maximo for assets in the predicted impact zone, check their current condition scores from Health, and automatically generate work orders for preventive inspections. All of this happens through the standardized MCP interface, without custom API integration code.

The MCP Server also opens the door for multi-agent orchestration. An organization could have one agent focused on reliability analysis, another on inventory optimization, and a third on scheduling. These agents can coordinate through the MCP Server, each contributing their specialized analysis to a unified workflow. IBM has indicated that the MCP Server is the first step in a broader strategy to make Maximo a platform that AI agents can operate on, rather than just a system that has AI features.

For administrators, the MCP Server is configured through the MAS admin interface. You control which API operations are exposed to external agents, set authentication and authorization policies, and monitor agent interactions through audit logs. Security is a critical consideration: the MCP Server supports OAuth 2.0 authentication and respects Maximo's security model, so external agents can only access data and perform actions that their assigned user role permits.

Here is a simplified example of configuring an MCP Server connection through the MAS admin CLI:

# Configure MCP Server endpoint
mas mcp-server create \
  --name "reliability-agent" \
  --description "External reliability analysis agent" \
  --auth-type oauth2 \
  --client-id "mcp-rel-agent-001" \
  --client-secret-env "MCPS_SECRET" \
  --allowed-apis "manage.assets.read,manage.workorders.create,manage.health.read" \
  --rate-limit "100/hour" \
  --audit-enabled true

# Verify the configuration
mas mcp-server list --verbose

This configuration creates an MCP Server endpoint that allows an external agent to read asset data, read health scores, and create work orders, but not modify existing records. The rate limit prevents runaway agent behavior, and audit logging ensures every interaction is recorded for compliance review.

Safety, Compliance, and HSE: The New Workflows

MAS 9.2 significantly expands the safety and compliance capabilities of the platform. In previous releases, safety features were scattered across applications: permit-to-work was a custom workflow in Manage, incident reporting was a manual process, and safety inspections were handled through the general inspection framework. MAS 9.2 brings these together into a cohesive set of HSE (Health, Safety, and Environment) workflows.

The new HSE Incident Reporter is a mobile-first application that allows field teams to capture incidents, complete inspections, and initiate permit-to-work processes directly from a mobile device. This is not just a form on a phone. The incident reporter uses the device's camera to capture photos and video, GPS to record location, and voice-to-text to record incident descriptions. The incident is routed through a configurable approval workflow, with notifications to safety officers and automatic creation of follow-up work orders.

Permit-to-work has been redesigned as a first-class workflow in MAS 9.2. In previous versions, permits were typically managed through custom applications or third-party solutions. The native permit-to-work workflow supports multiple permit types (hot work, confined space, electrical isolation, working at height), requires electronic sign-off from authorized personnel, and integrates with the work order lifecycle to ensure that work cannot begin until all required permits are approved.

The compliance benefits are significant. For organizations in regulated industries (oil and gas, utilities, nuclear, pharmaceutical), the ability to demonstrate a closed-loop safety process from incident identification through investigation, corrective action, and audit trail is essential. MAS 9.2 provides this out of the box, without the custom development that was previously required. The audit trail captures who approved each permit, when it was approved, what conditions were attached, and when the permit expired. This level of documentation is typically required for regulatory compliance in high-risk industries.

Asset-centric waste management is another new capability in 9.2. This feature allows organizations to track waste generation, storage, transportation, and disposal as asset-related activities. For organizations subject to environmental regulations, this provides the audit trail needed for compliance reporting. The waste management workflow integrates with the existing inventory and procurement systems in Manage, so waste containers can be tracked like any other asset, with associated costs, locations, and lifecycle status.

Contractor safety oversight is a related addition. Organizations that use external contractors for maintenance work can now manage contractor safety documentation, training verification, and permit-to-work approvals within Maximo. The contractor safety workflow verifies that contractors have the required certifications and training before they can be assigned to work orders, and it maintains an audit trail of all safety-related documentation. This capability is particularly valuable for organizations in the energy sector, where contractor safety management is subject to strict regulatory oversight.

Industry Solutions and Add-On Updates

MAS 9.2 introduces several new industry solutions and add-on products that extend the platform's reach into specific vertical markets. Maximo Vegetation Management, introduced in the September 2025 feature channel update and fully integrated in 9.2, is a new SaaS add-on for Maximo Manage that helps utilities and transportation organizations understand and manage the state of vegetation across their service areas. This is a significant addition for utilities where vegetation management is a major driver of reliability and maintenance costs.

Maximo Real Estate and Facilities (MREF) has been enhanced with a Lease Abstraction capability that uses retrieval-augmented generation (RAG) to extract key information from lease documents. For organizations managing large real estate portfolios, manual lease abstraction is a time-consuming and error-prone process. The RAG-based approach reads the lease document, identifies key terms (rent amounts, expiration dates, renewal options, maintenance responsibilities), and structures the data for use in the MREF application. This is one of the first applications of generative AI to document processing in the Maximo platform.

The Maximo Maintenance Costs Insights feature, introduced in 9.1 and refined in 9.2, integrates with IBM Apptio to provide comprehensive visibility into maintenance costs. The feature sends Maximo Manage asset, location, org, site, and work order cost data to IBM Apptio, which joins and prepares the data using predefined models. After analysis, Apptio sends the data back to Maximo Manage where it can be viewed in the Total Cost Maintenance (YTD) dashboard. This integration bridges the gap between maintenance operations and financial planning, which has been a persistent challenge for asset-intensive organizations.

The SAP Connector has been updated to use SAP Cloud Platform Integration (CPI) instead of the older SAP Process Orchestration. This is a necessary modernization, as SAP has been deprecating Process Orchestration in favor of CPI. The updated connector supports the same integration scenarios (purchase requisitions, purchase orders, goods receipts, invoices) but uses the modern CPI architecture, which is more scalable and easier to configure.

Technical Platform Improvements

Beyond the feature-level changes, MAS 9.2 includes several technical platform improvements that affect administrators, developers, and IT operations teams. Understanding these changes is essential for planning the upgrade and ensuring compatibility with existing customizations and integrations.

The database support matrix has expanded significantly. MAS 9.2 adds support for DB2 12.1, Oracle 26ai (once on-prem availability is confirmed by Oracle), and MongoDB 8.0. The Java runtime has been updated to Java 25, with Java 21 maintained for the Real Estate and Facilities module due to library compatibility constraints. BIRT has been upgraded to version 4.21, bringing improved chart rendering, better PDF export capabilities, and fixes for long-standing formatting issues. The Cloud Pak for Data dependency has been updated to CP4D 5.2, which affects the AI and analytics services.

For email communication, MAS 9.2 adds OAuth2 SMTP authentication for outgoing emails. This is a significant operational improvement, as many organizations have disabled basic SMTP authentication in favor of OAuth2 in response to security policies and compliance requirements. Previously, Maximo environments required workarounds like SMTP relays or service accounts with basic authentication enabled. With native OAuth2 support, Maximo can send email through Microsoft 365, Google Workspace, and other modern email providers without these workarounds. The configuration is done through the MAS admin interface:

{
  "smtpConfig": {
    "host": "smtp.office365.com",
    "port": 587,
    "authType": "OAUTH2",
    "clientId": "maximo-email-svc",
    "clientSecret": "${SECRET_REF}",
    "tenantId": "org-tenant-id",
    "fromAddress": "maximo-alerts@company.com",
    "useTLS": true
  }
}

The License Consumption Dashboard has been improved with more granular visibility into AppPoint usage across applications. Administrators can now see not just how many AppPoints are being consumed, but which specific applications and features are driving consumption. This helps organizations optimize their licensing and avoid unexpected overage charges. The dashboard shows consumption trends over time, peak usage periods, and comparisons against the licensed AppPoint pool.

Data import has been enhanced with improved error handling and validation. The previous data import process was functional but opaque: if an import failed, diagnosing the cause often required digging through server logs. The improved data import provides clear error messages at the row and column level, with suggestions for corrective action. The import process also supports larger files and parallel processing, which reduces import time for large datasets.

User Management and Security UI has been overhauled. The previous security administration interface was functional but cluttered, with common tasks buried in nested menus. The new interface prioritizes the most common administrative tasks: user creation, role assignment, security group management, and authentication configuration. The improved UI also supports managing unsupported languages and provides Graphite Bidi support for bidirectional text rendering, which is important for organizations operating in Arabic or Hebrew language environments.

Upgrade Planning: From 9.1 to 9.2

If you are currently on MAS 9.1, the upgrade to 9.2 is the smoothest upgrade path IBM has offered for the Maximo platform. Because both releases share the same architecture and the channel subscription model handles much of the upgrade automatically, the effort is significantly less than a major version jump. However, smooth does not mean trivial, and there are specific steps you should follow to ensure a successful upgrade.

The upgrade process follows the same pattern as the 9.0 to 9.1 upgrade. First, verify that your OpenShift Container Platform version meets the prerequisites. MAS 9.2 requires OCP 4.14 or later, and IBM recommends even-numbered OCP versions for compatibility with all applications, particularly Health, Predict Utilities, and Collaborate, which depend on IBM App Connect and Cloud Pak components. Update the IBM Operator Catalog in your OpenShift cluster, then approve the MAS Core operator upgrade through the OpenShift web console or the oc CLI.

Individual applications (Manage, Monitor, Predict, Health, Visual Inspection, Mobile) upgrade automatically if you have auto-approval enabled. If you use manual approval, you will need to approve each application operator update sequentially. After the upgrade, re-apply any custom configurations, verify integrations, and run regression testing. The following checklist covers the critical post-upgrade validation steps:

1. Verify all MAS Core services are running (identity, licensing, workspace, internal CA)
2. Validate Manage application health (database connectivity, UI access, API endpoints)
3. Test all integrations (REST APIs, Kafka, SAP/Oracle connectors, LDAP/SAML)
4. Re-apply custom UI themes, automation scripts, and configuration overrides
5. Run full regression testing on business-critical workflows
6. Validate data integrity using sample work orders, assets, and PM sequences
7. Test AI Service connectivity (if agentic features are enabled)
8. Verify mobile app connectivity and offline sync functionality
9. Review License Consumption Dashboard for unexpected changes
10. Document any issues and open PMRs with IBM support as needed

The key consideration for the 9.1 to 9.2 upgrade is the AI Service. If you want to use the new agentic AI workflows, Condition Insight, or the MCP Server, you need to ensure your AI Service is properly sized and configured. The AI Service requires GPU resources, so verify that your OpenShift cluster has sufficient GPU capacity or plan to add GPU nodes before the upgrade. The AI Service also requires connectivity to the watsonx.ai runtime, which may involve network configuration changes if your cluster has restricted egress.

For organizations on MAS 8.x, the upgrade to 9.2 follows the same path as the upgrade to 9.1. The process is more involved than a 9.1 to 9.2 upgrade, but the direct path from 8.x to 9.2 is supported. You will need to upgrade your OpenShift version if you are running an older release, update the IBM Operator Catalog, and perform a fresh installation of MAS 9.2 rather than an in-place upgrade. Your Maximo database can be upgraded in place, but the application layer requires a new deployment.

For those on Maximo 7.6, the direct upgrade path to 9.2 is the recommended route. IBM supports direct upgrades from 7.6.0.10, 7.6.1.2, and 7.6.1.3 to MAS 9.2. The process involves cloning your Maximo database, deploying MAS 9.2 on OpenShift, connecting to the cloned database, and activating the database upgrade. Plan for a 6 to 9 month timeline from assessment to go-live, with 2 to 3 months for assessment, 1 month for upgrade execution, 1 month for UAT, 1 month for go-live, and 2 months for hypercare.

Practical Implications

MAS 9.2 is a release that rewards organizations that have already moved to the 9.x architecture. If you are on 9.0 or 9.1, the upgrade to 9.2 is low-risk and high-value. The agentic AI workflows, MCP Server, and expanded safety features are all capabilities that can be adopted incrementally after the upgrade, so you do not need to configure everything on day one. Start with the core platform upgrade, validate your existing workflows, and then enable new features one at a time.

For organizations still on 8.x or 7.6, MAS 9.2 makes the case for upgrading even stronger. The gap between 8.x and 9.2 is now two major releases wide, and the agentic AI capabilities, MCP Server, and HSE workflows are features that cannot be backported. The longer you wait, the more technical debt you accumulate and the harder the eventual migration becomes.

The licensing model has not changed. MAS 9.2 uses the same AppPoint-based licensing as 9.0 and 9.1, with AppPoints shared across applications. The new features in 9.2 do not require additional AppPoint purchases if you already have an MAS 9.x license. However, some features like Condition Insight and the MCP Server may require specific application entitlements or add-on licenses. Check your license agreement or contact your IBM representative to confirm coverage before planning feature adoption.

Bottom Line

MAS 9.2 is the most feature-rich release in the 9.x line, and it establishes Maximo as a platform that AI agents can operate on, not just a system that has AI features. The agentic AI workflows, MCP Server, expanded HSE capabilities, new industry solutions, and technical improvements make it a compelling upgrade for any organization on 9.0 or 9.1. For those on 8.x or 7.6, the case for moving is clear: the direct upgrade path is supported, the features are compelling, and the support clock is ticking on older releases.

The upgrade from 9.1 to 9.2 is low-friction and can be completed in a matter of days for a well-managed environment. The upgrade from 8.x or 7.6 is a larger project, but the destination is now significantly more capable than it was a year ago. If you have been waiting for a reason to upgrade, MAS 9.2 is it.