CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

A well-structured, code-first skill body that is largely executable and clearly sequenced. Its weaknesses are SDK API drift in the templates, unverified placeholder credentials, and advanced patterns inlined where a one-level reference file would improve organization.

Suggestions

Fix SDK API accuracy: the low-level Python SDK has no '@server.tool()' decorator (use FastMCP's '@mcp.tool()' or register list_tools/call_tool handlers), and the TypeScript template should pass the ListToolsRequestSchema/CallToolRequestSchema constants to setRequestHandler.

Move 'Advanced Patterns' (external API integration, database access, resources) into a references/ file with clearly signaled one-level-deep links, and drop the 'You now have expertise' and 'What is MCP?' padding Claude doesn't need.

Add an error-recovery checkpoint after the MCP Inspector test step (e.g., what to check when the server fails to start or a tool call errors) and include the registration snippet for the TypeScript path, not just Python.

DimensionReasoningScore

Conciseness

The body is dominated by executable code with lean prose, but 'You now have expertise in building MCP servers' and the '## What is MCP?' section explain concepts Claude already knows. Minor over-explanation that could be trimmed — the 4 anchor, not the 5 'every token earns its place' anchor.

4 / 5

Actionability

Provides copy-paste-ready Python and TypeScript templates, install commands, registration JSON, and test commands, covering the common cases. Minor gaps keep it below 5: the '@server.tool()' decorator does not match the low-level Python SDK API, 'YOUR_API_KEY' is an unresolved placeholder, and the TypeScript 'setRequestHandler("tools/list")' call should pass a request schema.

4 / 5

Workflow Clarity

Setup, template, registration, and testing are clearly sequenced per language, with the MCP Inspector section serving as a verification checkpoint and the SQL example including a SELECT-only guard. Gaps — no error-recovery guidance and no registration step for the TypeScript path — fit the 4 anchor's 'most checkpoints present'.

4 / 5

Progressive Disclosure

A single-file skill with no bundle files present; sections are well-organized and navigable. The 'Advanced Patterns' section (external APIs, database access, resources) is inline content that would sit better in a references file — a minor organization gap matching the 4 anchor rather than 5.

4 / 5

Total

16

/

20

Passed

Description

83%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: concrete actions, an explicit 'Use when...' trigger clause, and a distinct MCP niche. Weaknesses are limited to slightly generic 'new capabilities' phrasing and missing common trigger synonyms.

Suggestions

Drop the generic 'that give Claude new capabilities' clause in favor of another concrete capability (e.g., exposing resources or prompts) to sharpen specificity.

Add natural trigger variations such as 'build an MCP server', 'connect Claude to an external service', or 'MCP integration' to broaden trigger-term coverage and reduce overlap ambiguity with generic integration skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Build MCP (Model Context Protocol) servers', 'add tools to Claude', 'integrate external services'), with 'give Claude new capabilities' being generic filler. Minor coverage gaps (resources, prompts, testing) keep it below the comprehensive 5 anchor.

4 / 5

Completeness

Explicitly answers both: what ('Build MCP (Model Context Protocol) servers that give Claude new capabilities') and when ('Use when user wants to create an MCP server, add tools to Claude, or integrate external services') with concrete trigger phrases. Matches the 5 anchor's structure exactly.

5 / 5

Trigger Term Quality

Natural phrases like 'create an MCP server', 'add tools to Claude', and 'integrate external services' match what users would say, but common variations such as 'build a server', 'MCP integration', or 'connect Claude to a service' are missing. Good coverage, a few natural terms absent — the 4 anchor.

4 / 5

Distinctiveness Conflict Risk

MCP server building is a clear niche with distinct triggers, but 'integrate external services' is broad enough to overlap with general API-integration skills. Mostly distinct with minor overlap risk — the 4 anchor, not 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Revision

33a5d85

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill