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).
93
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 94%
↑ 2.23xAgent success when using this skill
Validation for skill structure
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 with explicit 'Use when' guidance and good trigger term coverage across multiple technology stacks. The main weakness is the lack of specific concrete actions - it describes the purpose at a high level but doesn't enumerate what specific tasks the skill helps with (e.g., defining tools, handling resources, implementing prompts).
Suggestions
Add specific concrete actions like 'define tool schemas, implement resource handlers, configure authentication, structure server responses' to improve specificity.
Consider adding more user-intent trigger terms like 'LLM tools', 'Claude tools', or 'AI integrations' that users might naturally say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (MCP servers) and general purpose (enable LLMs to interact with external services), but lacks specific concrete actions like 'define tool schemas', 'handle authentication', or 'implement request handlers'. | 2 / 3 |
Completeness | Clearly answers both what ('Guide for creating high-quality MCP servers that enable LLMs to interact with external services through well-designed tools') and when ('Use when building MCP servers to integrate external APIs or services, whether in Python or Node/TypeScript'). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms: 'MCP', 'Model Context Protocol', 'MCP servers', 'external APIs', 'services', 'Python', 'FastMCP', 'Node', 'TypeScript', 'MCP SDK' - these are terms users would naturally use when seeking this skill. | 3 / 3 |
Distinctiveness Conflict Risk | MCP servers are a distinct niche with specific terminology (FastMCP, MCP SDK, Model Context Protocol). Unlikely to conflict with general API or server development skills due to the specialized MCP focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured workflow for MCP server development with excellent progressive disclosure and clear phase-based organization. However, it leans heavily on external references for concrete implementation details, making the main document more of a navigation guide than an actionable skill. The content could be more concise by removing conceptual explanations Claude already knows.
Suggestions
Add at least one minimal executable code example inline (e.g., a basic tool registration in TypeScript) rather than deferring all code to reference files
Remove or condense explanatory text like 'The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks' - Claude understands quality metrics
Tighten Section 1.1 'Understand Modern MCP Design' by converting prose explanations into bullet points or removing concepts Claude already knows about API design
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary explanation (e.g., explaining what MCP is, general statements about quality). Some sections like 'Understand Modern MCP Design' contain conceptual explanations that could be tightened. | 2 / 3 |
Actionability | Provides good structural guidance and references to external resources, but lacks concrete executable code examples within the main document. Most actionable content is deferred to reference files rather than shown inline. | 2 / 3 |
Workflow Clarity | Clear four-phase workflow with well-sequenced steps. Each phase has numbered sub-steps, and Phase 3 includes explicit build/test validation checkpoints. The evaluation phase includes verification requirements. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear overview pointing to one-level-deep reference files. References are well-signaled with descriptive links (e.g., '[📋 MCP Best Practices](./reference/mcp_best_practices.md)'). Content is appropriately split between overview and detailed guides. | 3 / 3 |
Total | 10 / 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.
- 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.