Epic Goal

Investigate (and if possible, implement) potential improvements to the MCP support in Developer Lightspeed, namely:

• MCP tool selection:
  • Allow users to select which MCP tool(s) they want called
  • May require new UI (which they consider stretch for 1.9), thus this may be scoped to just an investigation for 1.9
• Providing MCP server authentication/authorization:
  • Look at both internal-to-RHDH and external-to-RHDH (latter being prep work for "Bring-your-own MCP")
  • Depends on support being available in Lightspeed core

Because both of these items have dependencies (UI, Lightspeed Core), which may not be ready in time for 1.9, the only requirements for this epic will be to complete the investigations. 

Why is this important?

• These constitute necessary improvements to Developer Lightspeed to bring it in line with many standard MCP clients available today
• These improvements will enable us to implement "Bring-your-own MCP server" in a future release

Scenarios

1. Investigate MCP tool selection in Developer Lightspeed
   1. Stretch: Implementation (depends on UI, and possibly changes in Ligthspeed Core/llama-stack)
2. Investigate MCP server authentication / authorization
   1. Look at both internal-to-RHDH and external-to-RHDH
   2. Stretch: Implementation (depends on changes being available in Lightspeed Core)

Acceptance Criteria (Mandatory)

• Completed investigations for MCP tool selection
  • Design doc, PoC, etc
• Completed investigations for authentication/authorization to MCP servers
  • Design doc, PoC, etc
• As mentioned above, the implementations for each

Dependencies (internal and external)

1. ...

Previous Work (Optional):

Open questions::

1. …

Done Checklist

• Acceptance criteria are met
• Non-functional properties of the Feature have been validated (such as performance, resource, UX, security or privacy aspects)
• User Journey automation is delivered
• Support and SRE teams are provided with enough skills to support the feature in production environment