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

60

Quality

70%

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 ./.agents/skills/mcp-server-patterns/SKILL.md

The canonical home for this skill is mcp-server-patterns in affaan-m/ECC

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 skill is well-organized and clearly scoped, but defers its most actionable code (tool registration, transport setup) to external docs and repeats the 'check Context7/docs' caveat throughout, adding verbosity without executable detail. Tightening the repeated caveats and showing a complete minimal server example would lift the weaker dimensions.

Suggestions

Consolidate the repeated 'check Context7/official MCP docs' reminders into one note near the top instead of restating it in every section, and move the tool() vs registerTool() API-variation guidance into a single 'SDK version differences' subsection.

Add a complete, copy-paste minimal server example that actually registers one tool and one resource with a Zod schema and connects a stdio transport, instead of stopping at McpServer construction and deferring registration to external docs.

Provide a short sequenced build checklist (install → define schemas → register tools/resources → choose transport → connect) with a verify step (e.g. run the server and confirm it lists tools) to make the workflow explicit.

DimensionReasoningScore

Conciseness

The body is mostly efficient but repeats the 'check Context7/official MCP docs' caveat ~6 times and explains what MCP is ('The Model Context Protocol (MCP) lets AI assistants call tools...'), and scatters time-sensitive API-variation notes (tool() vs registerTool()) outside a dedicated section — matching 'mostly efficient but includes some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Executable code is given for install and server init, but the core actions — registering tools/resources and setting up stdio/HTTP transport — are explicitly deferred to external docs ('the exact API varies by SDK version... See the official MCP documentation') rather than shown, matching 'some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

Sections flow logically (When to Use → How It Works → Examples → Best Practices) but there is no explicit sequenced build workflow with checkpoints; the build path is implicit, matching 'sequence present but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

Content is organized into clear, well-labeled sections with no bundle files present and no nested references, matching 'good structure; most content appropriately placed; minor organization gaps'; not a 5 because the body is slightly over the ~50-line simple-skill threshold and the repeated doc-check asides could be consolidated.

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.

The description is strong: it explicitly covers both what the skill does and when to use it with concrete, domain-specific trigger phrases, and occupies a distinct niche. Minor room to improve keyword synonyms (e.g. 'Model Context Protocol') and frame items as actions.

DimensionReasoningScore

Specificity

Names the domain ('Build MCP servers with Node/TypeScript SDK') and lists several concrete capabilities — 'tools, resources, prompts, Zod validation, stdio vs Streamable HTTP' — which matches the 'lists several specific actions; minor gaps' anchor; not a 5 because the items are domain nouns more than discrete actions Claude performs.

4 / 5

Completeness

Explicitly states 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'), matching the anchor that requires both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like 'building or debugging an MCP server', 'tools, resources, prompts, validation, or transport choice' align with what a user would say; falls short of 5 because 'Model Context Protocol' is not surfaced as a synonym trigger and some variations are absent.

4 / 5

Distinctiveness Conflict Risk

'MCP server' is a clear niche with distinct triggers (building/debugging MCP servers, transport choice) and minimal overlap with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.