mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
76
66%
Does it follow best practices?
Impact
88%
1.60xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/0b1c2d3e-4f5a-6b7c-8d9e-0f1a2b3c4d5e/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly identifies its niche (MCP server development) and provides explicit 'Use when' guidance with framework-specific triggers. Its main weakness is that it could be more specific about the concrete actions it covers (e.g., defining tools, configuring transports, handling authentication) rather than staying at the high-level 'creating servers' framing.
Suggestions
Add specific concrete actions the skill covers, e.g., 'defining tools and resources, configuring transport layers, handling authentication, structuring server code' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (MCP servers) and a general action ('creating high-quality MCP servers that enable LLMs to interact with external services through well-designed tools'), but doesn't list multiple specific concrete actions like defining tools, handling authentication, setting up transport layers, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (creating high-quality MCP servers that enable LLMs to interact with external services through well-designed tools) and 'when' (explicitly states 'Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK)'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'MCP', 'Model Context Protocol', 'MCP servers', 'FastMCP', 'MCP SDK', 'external APIs', 'Python', 'Node', 'TypeScript', 'tools'. These cover the main variations a user building MCP servers would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | MCP server development is a very specific niche with distinct trigger terms (MCP, Model Context Protocol, FastMCP, MCP SDK). Unlikely to conflict with general coding skills or other integration-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has excellent structure and progressive disclosure, with well-organized phases and clear references to supporting documents. However, it is significantly too verbose—repeating references multiple times, explaining concepts Claude already knows, and providing abstract guidance where concrete code examples would be more valuable. The lack of executable code in the main skill file, combined with the verbosity, means it consumes substantial context budget without proportional actionable value.
Suggestions
Cut the content by 40-50%: remove explanations of known concepts (DRY principle, async/await, error handling basics), eliminate redundant reference links (each guide is mentioned 3-4 times), and tighten the design principles section to concise bullet points.
Add a minimal executable code example for both Python and TypeScript showing a complete working MCP server with one tool, so the skill provides copy-paste-ready starting points rather than only abstract instructions.
Add explicit validation feedback loops in Phase 2/3, e.g., 'After implementing each tool: 1. Compile/build 2. Run evaluation harness against that tool 3. If failures, fix and re-run 4. Only proceed to next tool when passing.'
Consolidate the Reference Files section with the inline references—list each resource exactly once with clear guidance on when to load it, rather than repeating them across multiple phases.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, explaining many concepts Claude already knows (what MCP is, what error handling means, what DRY principle is, how async/await works). There's significant redundancy—reference files are listed multiple times (e.g., the Python/TypeScript guides are referenced in Phase 1, Phase 2, Phase 3, and again in the Reference Files section). Design principles like 'Build for Workflows' and 'Optimize for Limited Context' are explained at length when they could be bullet points. | 1 / 3 |
Actionability | The skill provides some concrete guidance (XML evaluation format, specific commands like `python -m py_compile`, `npm run build`, `timeout 5s python server.py`) but lacks executable code examples for the core task of building an MCP server. Most guidance is descriptive rather than executable—it tells you what to do conceptually but delegates actual implementation details to external reference files. No copy-paste-ready server skeleton is provided. | 2 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced and logically organized, but validation checkpoints are weak. Phase 3 mentions testing but warns against running the server directly without providing a clear, step-by-step validation loop. There's no explicit 'validate -> fix -> retry' feedback loop for the implementation phase. The testing guidance is more cautionary than procedural. | 2 / 3 |
Progressive Disclosure | The skill effectively uses progressive disclosure with clear one-level-deep references to language-specific guides, best practices, and evaluation guides. References are well-signaled with emoji markers and descriptive labels, and the Reference Files section provides a clean navigation index. Content is appropriately split between the overview and detailed reference files. | 3 / 3 |
Total | 8 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- majiayu000/claude-skill-registry-data
- Commit
3dd3ac0
- 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.