mcp-integration

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with complete executable examples across all MCP server types and a clear implementation workflow. The main weaknesses are mild verbosity from restating basics Claude knows and some overlap between inlined sections and the reference files.

Suggestions

Trim the Overview paragraph and 'Process management'/'Use cases'/'Benefits' bullet lists that restate concepts Claude already knows, keeping only configuration-specific guidance.

De-duplicate the inlined 'MCP Server Types' and 'Authentication Patterns' sections by summarizing each briefly in the body and pointing to references/server-types.md and references/authentication.md for the detail already housed there.

Add an explicit validate-then-retry feedback loop into the numbered 'Implementation Workflow' (e.g., after step 5 test with `/mcp`; if the server does not appear, fix config and re-run) so checkpoints live inside the workflow rather than only in separate checklists.

Dimension	Reasoning	Score
Conciseness	The bulk is actionable config rather than conceptual prose, but the overview paragraph restates what MCP is and several 'Use cases'/'Benefits'/'Process management' bullets restate basics Claude already knows, so it could be tightened.	3 / 5
Actionability	Provides complete, copy-paste-ready JSON configs for every server type (stdio/SSE/HTTP/WS), concrete tool-naming format, allowed-tools frontmatter examples, and a 9-step implementation workflow with specific commands like `claude --debug` and `/mcp`.	5 / 5
Workflow Clarity	A clear numbered implementation workflow, a lifecycle sequence, and validation checklists with `/mcp` and debug-log verification are present, but the main workflow lacks inline validate-then-retry feedback loops within its steps.	4 / 5
Progressive Disclosure	Clearly signals one-level-deep references to real files (references/server-types.md, authentication.md, tool-usage.md, all present), but the body inlines substantial server-type and authentication detail that overlaps with those reference files.	4 / 5
	Total	16 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit 'Use when...' trigger guidance, natural keyword coverage including a file extension and transport synonyms, and a clearly distinct niche. Minor room to sharpen the 'what' into discrete concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain (MCP server integration into Claude Code plugins) and lists several concrete trigger-actions (add, integrate, configure, set up, connect), but the 'what' describes capability scope rather than enumerating discrete end-actions, so it falls just short of comprehensive.	4 / 5
Completeness	Explicitly answers both what ('Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins') and when ('This skill should be used when the user asks to...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user phrasings ('add MCP server', 'integrate MCP', 'connect external service') plus synonyms, a concrete file extension (.mcp.json), and transport-type variants (SSE, stdio, HTTP, WebSocket), giving comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	The niche is clear and specific (MCP integration within Claude Code plugins) and the triggers (.mcp.json, CLAUDE_PLUGIN_ROOT, specific transport types) are unlikely to fire for unrelated skills, minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (555 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/mcp-integration/SKILL.md
Commit: 6ed46da

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.