Name: mcp-builder
Rating: 52 (1 reviews)
Author: administrakt0r

mcp-builder

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.

Quality

58%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/mcp-builder/SKILL.md

The canonical home for this skill is mcp-builder in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

56%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 lays out a clear, well-sequenced four-phase workflow with real verification steps, but it is undermined by broken bundle references: all './reference/*.md' files are missing and the existing './scripts/' bundle is not wired in. Actionability and progressive disclosure suffer as a result.

Suggestions

Fix or remove the dangling './reference/*.md' links — either ship the referenced files (mcp_best_practices.md, node_mcp_server.md, python_mcp_server.md, evaluation.md) under './references/' or inline their essential content.

Connect the existing './scripts/' bundle (connections.py, evaluation.py, example_evaluation.xml) by referencing it by path from Phase 4 instead of the vague 'provided scripts'.

Deduplicate the reference-file listings (they appear in both the Process phases and the Reference Files section) and remove the verbatim Overview restatement of the description.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient process guidance rather than explanations of concepts Claude already knows, but the Overview repeats the description verbatim and the four './reference/*.md' links are restated across both the Process phases and the Reference Files section, so it could be tightened.	3 / 5
Actionability	It gives concrete executable commands (npm run build, npx @modelcontextprotocol/inspector, python -m py_compile) and real SDK URLs, but all implementation code is deferred to './reference/*.md' files that do not exist, leaving the core concrete guidance incomplete.	3 / 5
Workflow Clarity	Four sequenced phases with numbered substeps and an explicit Review/Test phase (build + MCP Inspector verification) provide clear checkpoints; it falls short of 5 because error-recovery feedback loops (validate -> fix -> retry) are not spelled out.	4 / 5
Progressive Disclosure	The structure is well designed with one-level-deep, clearly signaled references, but every './reference/*.md' path points to a directory that does not exist while the actual './scripts/' bundle is barely referenced, so the navigation does not lead to real content.	3 / 5
	Total	13 / 20 Passed

Description

61%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 clearly communicates a distinct niche (MCP server creation) with good natural keyword coverage, but it omits any 'Use when...' trigger guidance, capping completeness at 3. Tightening specificity with a few concrete actions and adding an explicit trigger clause would raise it.

Suggestions

Add a 'Use when...' clause stating when to invoke this skill (e.g. 'Use when building or scaffolding an MCP server, or when the user asks to create Model Context Protocol tools/integrations').

Enumerate 2-3 concrete actions (e.g. 'design tool schemas, implement transport, generate evaluation suites') to lift specificity toward 4-5.

Include natural synonyms/extensions a user might say (e.g. 'MCP server', 'Model Context Protocol integration', 'tool server') to push trigger-term coverage to 5.

Dimension	Reasoning	Score
Specificity	It names the domain ('Create MCP servers') and a concrete buildable artifact plus 'well-designed tools' to interact with external services, but does not enumerate several specific actions, so it matches the 'names domain and 1-2 concrete actions' anchor rather than the multi-action 4.	3 / 5
Completeness	It clearly answers 'what' (create MCP servers enabling LLM interaction) but has no 'Use when...' clause or equivalent trigger guidance, so per the cap rule completeness is held at 3 even though the 'what' is explicit.	3 / 5
Trigger Term Quality	It includes both the acronym and full name ('MCP', 'Model Context Protocol') plus natural terms like 'servers', 'LLMs', 'tools', and 'external services' that users building integrations would actually say, fitting 'good keyword coverage' rather than the single-keyword 3.	4 / 5
Distinctiveness Conflict Risk	MCP server building is a clear, narrow niche unlikely to trigger for unrelated skills, but without an explicit 'when' trigger phrase it does not reach the fully-distinct 5 anchor.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 10 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/mcp-builder/SKILL.md
Commit: 57c135b

Reviewed: 3 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.