CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

52

Quality

58%

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 ./.cursor/skills/mcp-server-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

A clear, well-structured overview of MCP server patterns that is honest about SDK variability, but it sacrifices concrete executability by hedging the main registration example and repeats the 'verify the docs' caveat across multiple sections.

Suggestions

Commit to one concrete, executable registration example for the current SDK version and move version-variant patterns into a clearly labeled 'SDK version differences' section or a reference file.

Consolidate the repeated 'check Context7 / official MCP docs' guidance into a single 'Verify current API' callout instead of restating it in nearly every section.

Present the build flow as a short numbered sequence (install → construct server → register tools/resources → choose transport → verify) so the steps are explicitly sequenced.

DimensionReasoningScore

Conciseness

Mostly efficient and well-organized, but it repeats the 'check Context7 or official MCP docs' caveat many times and re-explains that the SDK API varies across sections, which could be tightened into a single note.

2 / 3

Actionability

Provides some concrete code (install command, McpServer construction) but the central registration example is deliberately non-committal — 'some versions use... others use...' — offering multiple pseudocode shapes rather than one executable, copy-paste-ready pattern.

2 / 3

Workflow Clarity

The build sequence is implicit (install, set up server, register tools/resources, choose transport) but is presented as concepts rather than a numbered, validated workflow with checkpoints, which caps clarity at 2.

2 / 3

Progressive Disclosure

Has clear sections and one external reference (capability-surface-selection.md), but there are no bundle files in references/scripts/assets and the body keeps most material inline rather than splitting detailed reference content into separate files.

2 / 3

Total

8

/

12

Passed

Description

67%

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 specific, niche-targeted description that clearly conveys what the skill covers, but it omits an explicit 'Use when...' trigger clause and leans on technical jargon rather than natural user phrasings.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building or maintaining an MCP server, adding tools/resources, or choosing stdio vs HTTP transport.'

Soften jargon with more natural phrasings users would actually say, e.g. mention 'MCP server', 'MCP tools', or 'add tools to an assistant' alongside the technical terms.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'tools, resources, prompts, Zod validation, stdio vs Streamable HTTP' — naming specific SDK constructs and tasks rather than abstract actions.

3 / 3

Completeness

Clearly states what the skill does, but the 'when' is only implied — there is no explicit 'Use when...' clause in the description, which caps completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

Includes relevant terms ('MCP servers', 'Node/TypeScript SDK', 'stdio vs Streamable HTTP') but lacks the natural phrasings a user would actually say, and leans on technical jargon ('Zod validation', 'Streamable HTTP') over common variations.

2 / 3

Distinctiveness Conflict Risk

The 'MCP servers' niche is specific with distinct, technical triggers (MCP, stdio, Streamable HTTP) that are unlikely to overlap with or activate other skills.

3 / 3

Total

10

/

12

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.

Validation14 / 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
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.