hjemmesidekongen/mcp-creator
plugins/kronen/skills/mcp-creator/SKILL.md
Create and configure MCP server integrations for Claude Code plugins. Use when adding external service connections, setting up .mcp.json, configuring stdio/SSE/HTTP/WebSocket servers, integrating MCP tools into commands and agents, debugging MCP server connectivity issues, adding tool annotations, or configuring OAuth and API key authentication for MCP servers.
tools
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai mcp-creatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 5:16 PM100.1s9 files scanned
SKILL.md
- name:
- mcp-creator
- description:
- >
- user_invocable:
- false
- interactive:
- false
- depends_on:
- [plugin-creator]
- writes:
- []
- type:
- data_validation
- - name:
- portable_paths
- verify:
- All paths use ${CLAUDE_PLUGIN_ROOT}, no hardcoded absolute paths
- fail_action:
- Replace absolute paths with ${CLAUDE_PLUGIN_ROOT}
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- https://github.com/anthropics/claude-code/tree/main/plugins/plugin-dev/skills/mcp-integration
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- Adapted from Anthropic mcp-integration skill. Restructured for 80-line SKILL.md with project conventions.
MCP Creator
Create and configure MCP server integrations for Claude Code plugins.
When to trigger
- Adding external service connections to a plugin
- Setting up
.mcp.jsonconfiguration - Configuring stdio, SSE, HTTP, or WebSocket MCP servers
- Integrating MCP tools into commands or agents
- Debugging MCP server connectivity issues
Server types
| Type | Transport | Best for | Auth method | |------|-----------|----------|-------------| | stdio | Child process (stdin/stdout) | Local tools, custom servers, NPM packages | Env vars | | sse | HTTP + Server-Sent Events | Hosted services, cloud APIs | OAuth (auto) | | http | REST requests | API backends, token auth | Bearer/API key | | ws | WebSocket | Real-time streaming, low-latency | Bearer/headers |
Configuration methods
| Method | Location | When to use |
|--------|----------|-------------|
| .mcp.json | Plugin root | Multiple servers, clean separation (recommended) |
| mcpServers in plugin.json | .claude-plugin/plugin.json | Single server, simple plugins |
Tool naming
Format: mcp__plugin_<plugin-name>_<server-name>__<tool-name>
Pre-allow specific tools in command frontmatter via allowed-tools. Avoid wildcards.
Tool annotations
Add hints so Claude reasons about safety: readOnlyHint, destructiveHint, idempotentHint, openWorldHint. After build + tests pass, create evaluation.xml with 10 read-only Q&A pairs. Full process: references/process.md.
Related Skills
hjemmesidekongen/brand-strategy
development
VerifiedTrustedCommunity
Creates a brand from scratch through market research and interactive sparring. Runs competitive research via Perplexity, then guides the user through positioning, audience, voice, values, and content pillars. Produces the full brand guideline set at .ai/brand/{name}/. Use when building a new brand, defining brand strategy for a product, or when /våbenskjold:create is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-loader
testing
VerifiedTrustedCommunity
Loads brand guidelines from .ai/brand/{name}/ and makes them available to the current context. Progressive disclosure: L1 confirms brand exists, L2 loads summary, L3 loads specific files on demand. Use when a downstream skill or user needs brand context, or when /våbenskjold:apply is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-evolve
documentation
VerifiedTrustedCommunity
Guided reinvention of an existing brand guideline. Loads current brand from .ai/brand/{name}/, identifies what to keep vs change, and walks the user through targeted evolution. Preserves brand equity while updating positioning, voice, or values. Use when refreshing a brand or when /våbenskjold:evolve is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-audit
development
VerifiedTrustedCommunity
Codifies an existing brand from materials, samples, and references. Analyzes provided content to extract voice patterns, values, and positioning. Produces the same guideline format as brand-strategy. Use when a brand already exists but isn't documented, or when /våbenskjold:audit is invoked.
SKILL.mdUpdated Apr 5, 2026