CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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. Use when building or debugging an MCP server — tools, resources, prompts, validation, or transport choice.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/mcp-server-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 a reasonably organized, readable overview of MCP server patterns, but it hedges on the exact APIs (repeatedly deferring to external docs instead of committing to one executable pattern), repeats the same doc-lookup reminder five times, and provides no verification workflow for the debugging use case it claims to cover. It reads more as an annotated concept map than an executable playbook.

Suggestions

Pick the current SDK API and show one complete, copy-paste-ready tool registration example (name, description, Zod inputSchema, handler); move the alternative API shapes (tool() vs registerTool(), positional vs object args) into a short 'SDK version differences' reference file.

Add a minimal build-verify workflow — register a tool, start the server on stdio or HTTP, and test it from a real client (e.g. Claude Desktop or an MCP inspector) — so the 'debugging MCP registration and transport issues' trigger has a concrete, checkable sequence.

State the 'check Context7 / official MCP docs for current signatures' guidance once in the intro and remove the four repetitions in Core concepts, stdio, Examples, and SDK sections; also fix or remove the broken ../../docs/capability-surface-selection.md link.

DimensionReasoningScore

Conciseness

The reminder to 'check Context7 or the official MCP documentation' is repeated five times across sections, and the opening line explains what MCP is — a concept Claude already knows. The body is otherwise compact, fitting 'mostly efficient but includes some unnecessary explanation'.

3 / 5

Actionability

The npm install command and McpServer constructor snippet are executable, but tool/resource registration is rendered in prose across three possible API shapes ('positional args', object form, 'registerTool()') with no runnable example, and the stdio transport section defers to external docs ('The exact API varies by SDK version'). This is incomplete guidance with missing key details rather than a minor gap.

3 / 5

Workflow Clarity

Sections imply a conceptual order (concepts → transports → setup → best practices), but no build/verify sequence exists; despite the skill covering 'debugging MCP registration and transport issues', there is no step like register → launch → test with a client, and validation checkpoints are entirely absent.

3 / 5

Progressive Disclosure

Well-sectioned ~60-line overview with clear headers, but it inlines SDK API-version comparison detail that belongs in a reference file, and its single referenced path '../../docs/capability-surface-selection.md' does not exist (broken link) — minor organization gaps consistent with anchor 4.

4 / 5

Total

13

/

20

Passed

Description

87%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: it states concrete capabilities in third person, explicitly pairs a clear 'what' with a concrete 'Use when' trigger clause, and occupies a distinct niche. The only weaknesses are a slightly filler middle sentence about doc lookup and a few missing natural synonyms.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — 'tools, resources, prompts, Zod validation, stdio vs Streamable HTTP' — but the middle sentence ('Use Context7 or official MCP docs for latest API') is guidance rather than a capability, leaving minor gaps versus anchor 5's comprehensive coverage.

4 / 5

Completeness

Explicitly answers both: what ('Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP') and when ('Use when building or debugging an MCP server — tools, resources, prompts, validation, or transport choice') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrases like 'building or debugging an MCP server', 'tools', 'validation', and 'transport choice' are present and would be said verbatim, but common variations such as the spelled-out 'Model Context Protocol' or client names (Claude Desktop, Cursor) are missing.

4 / 5

Distinctiveness Conflict Risk

'MCP server' is a clearly defined niche with distinct triggers (SDK, Zod, stdio, Streamable HTTP) and no overlap with adjacent skills; it would not fire for the wrong skill.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

affaan-m/ECC

Path

skills/mcp-server-patterns/SKILL.md

Reviewed

Table of Contents

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.