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).

Quality

73%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/mcp-builder/SKILL.md

Quality

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 the 'what' portion is somewhat high-level—it could benefit from listing more concrete actions like defining tool schemas, handling authentication, or structuring server endpoints. Overall, it performs well for skill selection purposes.

Suggestions

Add more specific concrete actions to the 'what' portion, e.g., 'define tool schemas, handle authentication, structure request handlers, validate inputs' 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 'define tool schemas, handle authentication, implement request routing, validate inputs'.	2 / 3
Completeness	Clearly answers both 'what' (creating 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', 'external APIs', 'services', 'Python', 'FastMCP', 'Node', 'TypeScript', 'MCP SDK'. 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). 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 orchestration skill that effectively organizes a complex multi-phase workflow with good progressive disclosure to reference files. Its main weaknesses are moderate verbosity (explaining rationale Claude doesn't need, like why TypeScript is recommended), lack of concrete executable code in the main body (deferring almost everything to reference files), and insufficient validation/feedback loops in the workflow. The skill reads more like a project management guide than a hands-on technical reference.

Suggestions

Add at least one minimal but complete executable code example in the main body (e.g., a basic TypeScript MCP server with one tool) so the skill is actionable without loading reference files.

Remove explanatory rationale Claude doesn't need, such as why TypeScript is recommended ('AI models are good at generating TypeScript code...') and the MCP design philosophy section—focus on what to do, not why.

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 schemas match API responses → fix → retest.'

Dimension	Reasoning	Score
Conciseness	The skill contains some unnecessary explanation (e.g., explaining why TypeScript is recommended with multiple justifications, explaining what MCP is when Claude would know). The phase structure adds organizational overhead, and some sections like 'Understand Modern MCP Design' explain concepts at a level Claude doesn't need. However, it's not egregiously verbose.	2 / 3
Actionability	The skill provides structured guidance and references to external files, but lacks executable code examples in the main body. Implementation details are deferred to reference files (e.g., TypeScript/Python guides). The tool implementation section lists what to do (use Zod, add annotations) but doesn't show concrete executable examples. The evaluation XML example is a good concrete artifact.	2 / 3
Workflow Clarity	The four-phase workflow is clearly sequenced and logically ordered. However, validation checkpoints are weak—Phase 3 mentions running build and testing with MCP Inspector but lacks explicit feedback loops (e.g., what to do if tests fail, how to validate tool descriptions are adequate). For a process involving building servers that interact with external APIs, more explicit verification steps and error recovery guidance would be expected.	2 / 3
Progressive Disclosure	The skill excels at progressive disclosure with a clear overview structure pointing to well-organized reference files (mcp_best_practices.md, node_mcp_server.md, python_mcp_server.md, evaluation.md). References are one level deep, clearly signaled with emoji icons, and include brief descriptions of what each file contains. The 'Reference Files' section at the end provides a clean navigation index.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/devhub
Commit: 6338825

Reviewed: about 10 hours 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.