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).
91
73%
Does it follow best practices?
Impact
93%
2.21xAverage score across 10 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/anthropic-mcp-builder/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 relevant technology names. Its main weakness is that the 'what' portion is somewhat high-level—it could benefit from listing more specific concrete actions like defining tools, configuring transports, or handling authentication. Overall, the strong trigger terms and clear when-clause make it effective for skill selection.
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'defining tools and resources, configuring transports, handling authentication, structuring server responses' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description 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 it 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' ('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', and 'integrate'. These cover the main variations a user building MCP servers would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | MCP server development is a very specific niche with distinct trigger terms (MCP, Model Context Protocol, FastMCP, MCP SDK). This is unlikely to conflict with general coding skills or other integration-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that serves as an effective orchestration document for MCP server development, with good progressive disclosure to reference files. However, it suffers from moderate verbosity (duplicate reference sections, explanations of concepts Claude knows) and lacks concrete, executable code examples in the main body—relying heavily on external references that weren't provided in the bundle. The workflow is clear in sequence but missing explicit validation/error-recovery loops for a complex multi-step development process.
Suggestions
Add at least one minimal but complete executable code example inline (e.g., a 10-line TypeScript MCP server with one tool) so the skill is actionable even without loading reference files.
Add explicit validation checkpoints with feedback loops in Phase 3, e.g., 'If build fails: check type errors → fix → rebuild. If Inspector test fails: verify tool schema → check error messages → re-test.'
Remove the duplicated 'Reference Files' section at the bottom since all those links are already provided inline in the relevant phases, or consolidate into a single location to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized but includes some unnecessary explanation (e.g., explaining why TypeScript is recommended with multiple justifications, explaining what MCP is). Some sections like 'Understand Modern MCP Design' contain general advice Claude already knows (DRY principle, async/await for I/O). The reference files section at the end largely duplicates links already provided inline throughout the phases. | 2 / 3 |
Actionability | The skill provides a clear process structure and some concrete commands (npm run build, npx inspector, python -m py_compile), but lacks executable code examples for the core task of actually building an MCP server. Most guidance is at the level of 'create shared utilities' or 'implement tools' without showing concrete implementation patterns inline—those are deferred to reference files that aren't provided in the bundle. | 2 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced and logically ordered, but validation checkpoints are weak. Phase 3 mentions 'run build' and 'test with MCP Inspector' but lacks explicit feedback loops (e.g., what to do if build fails, how to verify tools work correctly before moving to Phase 4). For a multi-step process involving API integration and server development, the absence of explicit validate-fix-retry loops is notable. | 2 / 3 |
Progressive Disclosure | The skill effectively uses a hub-and-spoke model with clear one-level-deep references to language-specific guides, best practices, evaluation guide, and external SDK documentation. References are well-signaled with emoji markers and descriptive summaries of what each linked file contains. The main SKILL.md serves as a clear overview without inlining excessive detail. | 3 / 3 |
Total | 9 / 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
- boisenoise/skills-collections
- Commit
431bfad
- 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.