mcp-config

Configure MCP (Model Context Protocol) servers for Claude Code. Manage MCP servers at user or project scope with best practices to avoid context pollution.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude-code-setting/skills/mcp-config/SKILL.md

Quality

Content

50%

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

The content is concrete and well-structured with clear workflows, but it suffers from repetition, hard-coded personal paths that break copy-paste usability, and missing validation after destructive changes. Splitting reference material into bundle files and adding verification steps would meaningfully improve it.

Suggestions

Replace hard-coded '/Users/likai/' paths with '~/.claude.json' or a portable variable and parameterize 'server-name' so the cleanup scripts are executable as written.

Consolidate the repeated dos/don'ts from Critical Concepts, Best Practices, Summary, and Configuration Priority into a single section to reduce token cost.

Add post-change validation (re-run the status check, confirm JSON validity, verify the MCP no longer loads) after destructive cleanup steps to provide a proper feedback loop.

Move the Common MCP Servers catalog and the cleanup Python scripts into reference/script bundle files and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body does not explain concepts Claude already knows, but the same dos/don'ts are restated across Critical Concepts, Best Practices, Summary, and Configuration Priority, so it could be tightened considerably.	2 / 3
Actionability	There is plenty of concrete code, but the Python cleanup scripts hard-code '/Users/likai/.claude.json' and use a literal 'server-name' placeholder, so they are not copy-paste ready as the level-3 anchor requires.	2 / 3
Workflow Clarity	The Configuration Workflow and cleanup example give a clear numbered sequence with a pre-change status check, but destructive edits lack post-change validation, which per the guidelines caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a monolithic 330-line file with no bundle references, and content that could be split out (the Common MCP Servers catalog, cleanup scripts) is inline.	2 / 3
	Total	8 / 12 Passed

Description

57%

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

The description is clearly scoped to a distinct niche and uses some natural trigger terms, but it relies on generic action verbs and omits an explicit 'Use when...' clause. Adding concrete actions and an explicit trigger clause would raise both specificity and completeness.

Suggestions

Add an explicit 'Use when...' clause listing natural scenarios, e.g. 'Use when adding, removing, or troubleshooting MCP servers, or when MCPs load in unwanted sessions.'

Replace generic verbs with concrete actions: 'Add, remove, and relocate MCP servers across user and project scope' instead of 'Configure/Manage'.

Drop or relocate the jargon phrase 'best practices to avoid context pollution' and include user-natural terms like 'add' and 'set up' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	It names the domain and two actions ('Configure MCP ... servers', 'Manage MCP servers'), but the verbs are generic and it does not list multiple specific concrete actions, so it falls short of the level-3 anchor.	2 / 3
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms like 'MCP (Model Context Protocol) servers' and 'Claude Code' are present, but common action variations users would say ('add', 'install', 'set up', 'remove') are missing and 'context pollution' is jargon rather than a user trigger.	2 / 3
Distinctiveness Conflict Risk	The MCP-for-Claude-Code niche is narrow with distinct triggers and is unlikely to conflict with other skills, matching the level-3 anchor.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: libukai/awesome-agent-skills
Path: plugins/claude-code-setting/skills/mcp-config/SKILL.md
Commit: fef729a

Reviewed: 2 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.