mcp-server-patterns

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

Quality

63%

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 ./.cursor/skills/mcp-server-patterns/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.

The body is well-structured as a single-file overview with clear navigation, but it re-explains known concepts, hedges the core registration API across versions without one executable pattern, and lacks an ordered build-and-verify workflow with validation checkpoints.

Suggestions

Trim the re-explanation of what MCP/tools/resources/prompts are and consolidate the repeated "check the docs / Context7" reminders into a single prominent note.

Pick one current registration pattern and show a complete, copy-paste-ready tool+resource example, moving the per-version alternatives into a clearly labeled "SDK version differences" aside.

Add a short ordered build-and-verify workflow (install -> construct server -> register tools/resources -> run/inspect -> verify against current docs) with an explicit validation checkpoint before declaring the server ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but re-explains concepts Claude already knows (what MCP, tools, resources, and prompts are) and repeats the "check Context7 / official MCP docs" deferral phrasing several times near-verbatim.	3 / 5
Actionability	It provides a concrete npm-install and server-construction snippet, but the tool/resource registration guidance is hedged across multiple SDK versions ("registerTool() or tool()", "some versions use... others use...") with no single copy-paste-ready pattern and frequent doc deferrals.	3 / 5
Workflow Clarity	Content is organized by topic rather than as a sequenced build workflow, and there are no explicit validation checkpoints or feedback loops despite the stated risk of API-version mismatches during registration and transport setup.	3 / 5
Progressive Disclosure	This is a single, well-organized file under roughly 50 lines with clear section headers and one-level external doc references, fitting the simple-skill exception for progressive disclosure.	5 / 5
	Total	14 / 20 Passed

Description

70%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.

The description is specific and clearly scoped to MCP server building with concrete technology anchors, but it omits any explicit "Use when..." trigger guidance, capping its completeness. It is distinctive and low-conflict but slightly technical-leaning in its trigger terms.

Suggestions

Add an explicit trigger clause, e.g. "Use when building or maintaining MCP servers, adding tools/resources/prompts, or choosing between stdio and Streamable HTTP transports."

Soften the trigger terms with a couple of natural user phrasings (e.g. "MCP", "Model Context Protocol server") to broaden keyword coverage.

Reframe a few capability building blocks as concrete actions (e.g. "register tools, resources, and prompts") to nudge specificity from 4 to 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability building blocks ("tools, resources, prompts, Zod validation, stdio vs Streamable HTTP") rather than vague language, though it names components more than discrete actions.	4 / 5
Completeness	It gives a clear "what" (build MCP servers with the listed features) but the description field lacks any "Use when..." trigger clause; per the guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant natural keywords like "MCP servers", "Node/TypeScript SDK", "tools, resources, prompts", and "stdio vs Streamable HTTP" that a user building MCP servers would say, with only minor natural-synonym gaps.	4 / 5
Distinctiveness Conflict Risk	"Build MCP servers with Node/TypeScript SDK" is a clear, narrow niche with distinct triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: .cursor/skills/mcp-server-patterns/SKILL.md
Commit: d8409a4

Reviewed: 5 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.