MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
40
27%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent/skills/mcp-builder/SKILL.mdQuality
Discovery
32%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 identifies a specific technical domain (MCP servers) but relies on abstract category labels rather than concrete actions. It critically lacks any 'Use when...' guidance, making it difficult for Claude to know when to select this skill. The trigger terms are too technical and miss natural user language variations.
Suggestions
Add an explicit 'Use when...' clause with trigger phrases like 'building MCP servers', 'implementing Model Context Protocol', 'creating MCP tools', or 'server-side protocol implementation'.
Replace abstract terms like 'best practices' with concrete actions such as 'implement tool handlers', 'define resource schemas', 'structure server responses', or 'handle protocol messages'.
Include natural user language variations like 'MCP server', 'protocol server', 'tool server', 'MCP integration' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (MCP server building) and mentions some areas (tool design, resource patterns, best practices), but these are high-level categories rather than concrete actions like 'create handlers' or 'implement tool schemas'. | 2 / 3 |
Completeness | Describes what at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing explicit trigger guidance caps this at 2, but the 'what' is also weak. | 1 / 3 |
Trigger Term Quality | Includes 'MCP' and 'Model Context Protocol' which are relevant technical terms, but misses natural user phrases like 'build an MCP server', 'create tools', 'server implementation', or 'protocol integration'. | 2 / 3 |
Distinctiveness Conflict Risk | 'MCP' and 'Model Context Protocol' provide some distinctiveness, but 'tool design' and 'best practices' are generic enough to potentially overlap with other development or architecture skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a reference card or cheat sheet than actionable guidance for building MCP servers. While the table-based organization is clean, the content lacks executable code examples, concrete implementation steps, and clear workflows. Claude would struggle to actually build an MCP server from this guidance alone.
Suggestions
Add executable TypeScript code examples showing minimal server setup, tool registration, and resource handling - not just descriptions of what they should contain
Include a step-by-step workflow for creating a new MCP server: init project → define tools → register handlers → configure transport → test → deploy
Remove the 'What is MCP?' and basic concept explanations - Claude knows these; focus on implementation specifics
Add concrete input/output examples for tools showing actual JSON schemas and response formats
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient with good use of tables, but includes some explanatory content Claude already knows (e.g., 'What is MCP?' section, basic definitions). Could be tighter by removing conceptual explanations. | 2 / 3 |
Actionability | Almost entirely descriptive with no executable code examples. Tables describe concepts but don't show how to implement them. Missing concrete code for server setup, tool registration, or resource handling. | 1 / 3 |
Workflow Clarity | No clear workflow for building an MCP server. Content is organized as reference tables but lacks step-by-step guidance, validation checkpoints, or sequenced instructions for creating a working server. | 1 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but everything is inline in one file. No references to external files for detailed implementation guides, API references, or examples that would benefit from separation. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
7114206
Table of Contents
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.