-
Spike
-
Resolution: Unresolved
-
Major
-
None
-
None
-
None
-
Future Sustainability
-
5
-
False
-
-
False
-
-
-
-
None
Value Statement
We need a MCP Server for ACM Search -
- The data data contained by ACM Search is not easily available anywhere else (without having to make individual calls to each the managed clusters). So it is unique in that sense.
- MCP Server is a key building block for Lightspeed, customers building their own agents using our MCP Servers etc
Why is this a spike -
- Code is not GA quality
Why is code not GA Quality -
- we need to also evaluate search mcp server built on existing GraphQL API and
- evaluate pros and cons between the 2 implementations to see which is the recommended way.
- and then GA harden that code.
Definition of Done for Engineering Story Owner (Checklist)
- The MCP Server can be deployed on a Hub cluster and queried from claude code and claude desktop
- Code is checked into a repo
Development Complete
- The code is complete.
- Functionality is working.
- Any required downstream Docker file changes are made.
Tests Automated
- [ ] Unit/function tests have been automated and incorporated into the
build. - [ ] 100% automated unit/function test coverage for new or changed APIs.
Secure Design
- [ ] Security has been assessed and incorporated into your threat model.
Multidisciplinary Teams Readiness
- [ ] Create an informative documentation issue using the [Customer
Portal_doc_issue template](
https://github.com/stolostron/backlog/issues/new?assignees=&labels=squad%3Adoc&template=doc_issue.md&title=),
and ensure doc acceptance criteria is met. Link the development issue to
the doc issue. - [ ] Provide input to the QE team, and ensure QE acceptance criteria
(established between story owner and QE focal) are met.
Support Readiness
- [ ] The must-gather script has been updated.