mcp-builder

Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/mcp-builder/SKILL.md

Quality

Content

57%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.

A highly actionable skill with strong executable code examples for both Python and TypeScript, but it is weighed down by conceptual padding, lacks validation feedback loops in its build workflow, and keeps all content inline rather than using progressive disclosure.

Suggestions

Remove the 'What is MCP?' explainer and the 'You now have expertise' intro; assume Claude knows the protocol and lead with the build steps.

Add an explicit validate-then-fix feedback loop (e.g. run the MCP Inspector, read the error, fix, re-run) and strengthen the SQL example with a real validation/rollback pattern instead of only a SELECT guard.

Split the TypeScript template and Advanced Patterns into referenced files (e.g. references/typescript.md, references/advanced.md) and keep SKILL.md as a concise overview that links one level deep.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient code, but the intro ('You now have expertise...') and the 'What is MCP?' section explain what MCP is and how it works — concepts Claude already knows — which is padding that could be trimmed.	3 / 5
Actionability	Provides complete, copy-paste-ready Python and TypeScript server templates plus concrete advanced examples and test commands; minor gaps like the 'YOUR_API_KEY' placeholder and the lower-level TypeScript handler style keep it just below a 5.	4 / 5
Workflow Clarity	The Quick Start is clearly numbered (setup, template, register) and ends with a Testing section, but there are no explicit validation checkpoints or error-recovery feedback loops, and the destructive-capable SQL example only has a weak SELECT guard with no validation cycle.	3 / 5
Progressive Disclosure	Section headers give reasonable structure, but at ~210 lines everything is inlined into one monolithic SKILL.md with no bundle files or one-level-deep references; the TypeScript variant and advanced patterns are content that clearly belongs in separate referenced files.	3 / 5
	Total	13 / 20 Passed

Description

78%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 that explicitly covers both what and when with concrete, natural trigger phrases. It could be sharper by dropping the abstract 'give Claude new capabilities' padding and naming more specific operations.

Suggestions

Replace the abstract 'that give Claude new capabilities' with concrete operations, e.g. 'expose tools, resources, and prompts to Claude'.

Add a synonym or file/term variant (e.g. 'Model Context Protocol' or '.mcp') to broaden natural trigger coverage.

Tighten the 'integrate external services' trigger to reduce overlap with generic API-integration skills, e.g. 'integrate external services via the Model Context Protocol'.

Dimension	Reasoning	Score
Specificity	Names the domain and three actions ('Build MCP servers', 'add tools to Claude', 'integrate external services'), but 'give Claude new capabilities' is abstract padding and the actions stay high-level rather than naming concrete operations like exposing tools/resources/prompts.	3 / 5
Completeness	It clearly states what the skill does ('Build MCP servers that give Claude new capabilities') and explicitly answers when via a 'Use when' clause with three concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Phrases like 'create an MCP server', 'add tools to Claude', and 'integrate external services' are natural user language with good coverage, though it lacks synonyms or file-extension variants that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	MCP server building is a clear niche with distinct triggers and minimal conflict risk, but 'integrate external services' and 'add tools to Claude' could overlap with general API-integration or tooling skills, keeping it just below a 5.	4 / 5
	Total	16 / 20 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: shareAI-lab/learn-claude-code
Path: skills/mcp-builder/SKILL.md
Commit: 0dcafa2

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.