Skip to content

refactor: improved red-hat-security-mcp-setup to be agent agnostic#119

Open
lkrzyzanek wants to merge 1 commit into
RHEcosystemAppEng:mainfrom
lkrzyzanek:red-hat-security-mcp-setup-improvements
Open

refactor: improved red-hat-security-mcp-setup to be agent agnostic#119
lkrzyzanek wants to merge 1 commit into
RHEcosystemAppEng:mainfrom
lkrzyzanek:red-hat-security-mcp-setup-improvements

Conversation

@lkrzyzanek

@lkrzyzanek lkrzyzanek commented Jun 9, 2026

Copy link
Copy Markdown

Summary

Added claude CLI support with evaluation script (requires interactive mode) and generic "mcp.json" way.

The skill itself now also tries to trigger authentication and verifies it during the setup.

Pack(s) affected

  • ocp-admin
  • rh-ai-engineer
  • rh-automation
  • rh-basic
  • rh-developer
  • rh-sre
  • rh-virt
  • Other / repo-wide

Change type

  • New skill
  • New agent
  • New pack
  • Update existing skill / agent
  • MCP server config (mcps.json)
  • Docs / README
  • CI / tooling
  • Federation (external pack)

Contribution method

  • Created/imported with /agentic-contribution-skill
  • Manual contribution (validated with make validate + make validate-skill-design-changed)

Pack-persona alignment (new skills only)

CLAUDE.md compliance

  • Agents orchestrate skills; no direct MCP/tool calls in agents
  • Skills are single-purpose task executors
  • Skills encapsulate all tool access (MCP tools invoked only inside skills)
  • Document consultation: file is read with the Read tool, then declared to the user
  • No credentials hardcoded; env vars used via ${VAR} references
  • Human-in-the-loop confirmation added for any destructive or critical operations

Federation request (external pack)

  • Repository URL:
  • Pack path:
  • Ref:
  • License:
  • Contact:

Validation

  • make validate passes locally
  • New/changed skills have valid YAML frontmatter (name, description)
  • New/changed agents have valid YAML frontmatter (name, description)

@lkrzyzanek lkrzyzanek force-pushed the red-hat-security-mcp-setup-improvements branch 2 times, most recently from 5f37490 to 189325e Compare June 9, 2026 12:49
…pc.json) and claude native

added evals script for claude
@lkrzyzanek lkrzyzanek force-pushed the red-hat-security-mcp-setup-improvements branch from 189325e to fcc0eda Compare June 9, 2026 12:53
Comment on lines +56 to +59
- Enable the `/red-hat-cve-explainer` skill to use live MCP tools instead of web fallback

NOT for:
- CVE analysis (use `/red-hat-cve-explainer` instead)

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what's the reason to mention the /red-hat-cve-explainer skill here?

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Claude add it as a hint for next step
At some degree it make sense to navigate user what to do next.

But I can remove it if it doesn't fit into whole picture.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants