mcp-developer

Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up stdio/HTTP/SSE transport layers, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold complete MCP server/client projects using TypeScript or Python SDKs.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

85%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: a sequenced workflow with validation/feedback loops, two executable SDK examples, and clean progressive disclosure via a reference table. Verbosity is mild and concentrated in the generic MUST/MUST NOT constraint lists.

Suggestions

Tighten the intro line — it repeats the frontmatter description and adds little that the workflow doesn't already show.

Replace generic MUST DO/MUST NOT DO items ('Implement comprehensive error handling', 'Test protocol compliance thoroughly') with concrete, verifiable guidance or drop them in favor of the reference files.

Note that `fetchWeather`/`fetch_weather` are stubs; either inline a minimal real implementation or link to where the fetch pattern lives to make the examples fully runnable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, a tight numbered workflow, and a well-structured reference table, but the redundant intro line and the somewhat generic MUST DO/MUST NOT DO lists (e.g. 'Implement comprehensive error handling') could be trimmed.	4 / 5
Actionability	Two concrete, mostly copy-paste-ready code examples plus specific commands (`npx @modelcontextprotocol/create-server`, `npx @modelcontextprotocol/inspector`) and an expected tool-call flow, with only minor gaps from the stub `fetchWeather`/`fetch_weather` placeholders.	4 / 5
Workflow Clarity	The 6-step Core Workflow is clearly sequenced with an explicit validation checkpoint (step 5 inspector) and feedback loops for both schema-validation and malformed-response failures, matching the error-recovery anchor.	5 / 5
Progressive Disclosure	The body is a concise overview with a clear reference table pointing one level deep to five real, well-signaled bundle files, each with a 'Load When' navigation cue — all referenced paths verified to exist in references/.	5 / 5
	Total	18 / 20 Passed

Description

92%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: third-person/infinitive voice, concrete actions, explicit 'Use when' trigger, and a clearly distinct niche. The only minor gap is omitting the spelled-out 'Model Context Protocol' synonym in the description text.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'implement tool handlers, configure resource providers, set up stdio/HTTP/SSE transport layers, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold complete MCP server/client projects' — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both what (building/debugging/extending MCP servers and clients plus the enumerated sub-tasks) and when ('Use when building, debugging, or extending MCP servers or clients...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keywords ('MCP servers or clients', 'tool handlers', 'schemas with Zod or Pydantic', 'TypeScript or Python SDKs') that users would actually say, but the spelled-out 'Model Context Protocol' synonym is absent from the description itself.	4 / 5
Distinctiveness Conflict Risk	MCP is a clear niche with distinct triggers (MCP servers/clients, JSON-RPC, Zod/Pydantic schemas, stdio/SSE/HTTP transports) and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jeffallan/claude-skills
Path: skills/mcp-developer/SKILL.md
Commit: 882ef55

Reviewed: 6 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.