Feature Overview

This feature involves creating a prototype of a Model Context Protocol (MCP) server that exposes Red Hat Advanced Cluster Management (ACM) Search data and capabilities to external AI models and agents. This will enable natural language queries and AI-driven workflows for managing Kubernetes clusters.

RHACM Search MCP (Slide Deck)
Hybrid Platform MCP Servers FAQ

Goals

This Section: Provide high-level goal statement, providing user context
and expected user outcome(s) for this feature

• Create a functional MCP server prototype that can be consumed by an MCP client (e.g., an LLM).
• Expose key Search data as structured resources and API tools via the MCP.
• Validate the feasibility, performance, and security of using the MCP to enable AI-driven interactions with ACM Search.
• Gather developer and user feedback on the prototype to inform the future direction of AI-enabled features in ACM.

Requirements

This Section: A list of specific needs or objectives that a Feature must
deliver to satisfy the Feature.. Some requirements will be flagged as MVP.
If an MVP gets shifted, the feature shifts. If a non MVP requirement slips,
it does not shift the feature.

(Optional) Use Cases

This Section:

Main success scenarios - high-level user stories:

• As an AI assistant user, I want to be able to ask "How many clusters are in my environment?" and receive a correct answer from the ACM Search data.
• As a developer using an AI-integrated IDE, I want to ask "Show me all pods in the acm-monitoring namespace" and have the Search MCP server retrieve that data.
• As an ACM administrator, I want to use natural language commands to find resources that match specific criteria, such as "Find all non-compliant policies in the production cluster."

Alternate flow/scenarios - high-level user stories:

• If a user's query is ambiguous, the MCP server should provide the LLM with sufficient context to ask for clarification.
• The prototype should handle basic security considerations, such as not exposing unauthorized data, even to the LLM.

Questions to answer

• What level of support are we providing around this MCP server?
  • Do we state specific models / agentic tools?
• What is the level of lifecycle support needed here?
• What level of program enablement do we need?
  • Need to establish that this is a separate deliverable from core ACM/MCE (like Gatekeeper)
  • Versioning
  • Skills transfer
• Is HPBU co-locating all the portfolio MCP servers centrally somewhere for easier user discovery?
• Does this get doc-ed with core ACM documentation?
• Do we only align this MCP server feature release with 2.16; or do we allow use on current supported versions of ACM?
  • HPBU FAQ answer:  "MCP servers should support the widest skew of underlying product versions that is possible."
• Do we only support the Tech Preview for tools like Claude Code; or do we open support for the OLS integration too?
  • OLS integration provides much lesser quality results.

Out of Scope

• This feature is a prototype and is NOT a production-ready, highly available service.
• Implementing a full-fledged chat UI or agent on the client-side. This feature focuses only on the MCP server prototype.
  • We will use existing client-side chat interfaces such as Claude Code/Desktop to validate.
  • This work will target an integration with OpenShift Lightspeed at a later time.
• Complex multi-step actions or "agents" that chain multiple tool calls together.
• Writing data to the database (mutations). This will be a read-only prototype.
• Implementing a long-term security model; the prototype will use a basic proof-of-concept authentication and authorization method.

Background, and strategic fit

This Section: What does the person writing code, testing, documenting
need to know? What context can be provided to frame this feature?

Assumptions

• ...

Customer Considerations

• ...

Documentation Considerations

Questions to be addressed:

• What educational or reference material (docs) is required to support this
  product feature? For users/admins? Other functions (security officers, etc)?
• Does this feature have a doc impact?
• New Content, Updates to existing content, Release Note, or No Doc Impact
• If unsure and no Technical Writer is available, please contact Content
  Strategy.
• What concepts do customers need to understand to be successful in
  [action]?
• How do we expect customers will use the feature? For what purpose(s)?
• What reference material might a customer want/need to complete [action]?
• Is there source material that can be used as reference for the Technical
  Writer in writing the content? If yes, please link if available.
• What is the doc impact (New Content, Updates to existing content, or
  Release Note)?