-
Epic
-
Resolution: Done
-
Major
-
None
-
None
-
None
-
MCP Tools for the Software Catalog
-
False
-
-
False
-
Done
-
RHDHPLAN-43 - Model Context Protocol (MCP) Server in Red Hat Developer Hub
-
0% To Do, 0% In Progress, 100% Done
-
-
Epic Goal
Provide MCP tools that can query and interact with the software catalog, allowing MCP clients to fetch catalog entities, retrieve important metadata, and register/unregister entities.
Why is this important?
- …
Scenarios
- Backstage catalog search
- Search entities in the Backstage catalog (Components, Resources, APIs, Systems, etc). The tool should support searching catalog entities based on input, and retrieving catalog entities by name, kind, and type.
- Backstage catalog metadata retrieval / interaction
- Call the Backstage API to retrieve the metadata / catalog yaml of a given RHDH catalog entity, and properly format the data to allow the MCP client to properly manipulate the response (e.g. “retrieve the API spec for “component-123’s API”
- Register / unregister catalog entities
- Provide actions to register / unregister new catalog entities (note: creation of catalog entities is out of scope), provided the user has sufficient permissions to do so. Authentication should be via specifically configured static token with catalog write permissions.
- The tool should be able to take a given remote catalog-info yaml, and make the necessary Backstage API calls to register it with the catalog. The tool should be able to unregister specified catalog entities..
Acceptance Criteria (Mandatory)
- One or MCP plugins implementing the functionality listed above (one tool per function)
- Instructions to configure auth for the catalog register/unregister tool
- CI - MUST be running successfully with tests automated
- Release Technical Enablement - Provide necessary release enablement details and documents.
- ...
Dependencies (internal and external)
- ...
Previous Work (Optional):
- …
Open questions::
- …
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
