building-mcp-servers

1 stars 2 forks
17
B

Guides creation of high-quality MCP (Model Context Protocol) servers that enable LLMsto interact with external services through well-designed tools. Use when building MCPservers to integrate external APIs or services, whether in Python (FastMCP) orNode/TypeScript (MCP SDK). Covers tool design, authentication, Docker deployment,and evaluation creation. NOT when consuming existing MCP servers (use the server directly).

Also in: docker javascript kubernetes

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install mjunaidca/mjs-agent-skills/building-mcp-servers
skilz install mjunaidca/mjs-agent-skills/building-mcp-servers --agent opencode
skilz install mjunaidca/mjs-agent-skills/building-mcp-servers --agent codex
skilz install mjunaidca/mjs-agent-skills/building-mcp-servers --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/mjunaidca/mjs-agent-skills
2. Copy the agent skill directory:
cp -r mjs-agent-skills/.claude/skills/building-mcp-servers ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Stars
1
Forks
2
Type
Technical
Meta-Domain
development
Primary Domain
python
Market Score
17

Agent Skill Grade

B
Score: 80/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
24/30
Ease of Use
22/25
Writing Style
8/10
Utility
17/20
Modifiers: -3

Areas to Improve

  • Missing TOC in SKILL.md
  • Redundant transport information
  • Verbose workflow steps

Recommendations

  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-24

Developer Feedback

I came across your MCP servers skill and appreciated how you're tackling the server-client abstraction—it's a pattern that doesn't get enough attention in most tutorials, but your approach to it seems practical rather than theoretical.

Links:

The TL;DR

You're at 80/100, solidly in B territory. This is based on Anthropic's skill evaluation framework. Your strongest area is Ease of Use (22/25)—the metadata and discoverability are solid—but you're losing points in Progressive Disclosure Architecture (24/30) because your main file includes implementation details that belong in references, and Utility (17/20) because SKILL.md lacks any inline code examples.

What's Working Well

  • Clear metadata with good triggers: Your description nails the use cases ("MCP servers", "FastMCP", "Python", "TypeScript") and the NOT-when clause prevents misuse—that's the kind of specificity that helps users know if this is for them
  • Solid reference structure: Five focused reference files covering task patterns, best practices, Python/Node examples, and evaluation—no nested subdirectories, which keeps navigation flat and efficient
  • Practical workflow phases: Four clear phases from planning to deployment show you understand the actual development lifecycle, not just the theory

The Big One: Missing TOC and Inline Examples

Your SKILL.md is 192 lines but has no table of contents, making navigation harder than it needs to be. More importantly, you've got great examples buried in the references but none in the main file. When someone loads this skill, they see workflow descriptions but zero code samples—that's a usability gap.

Fix: Add a TOC at the top (## Table of Contents with anchor...

Report Security Issue

Found a security vulnerability in this agent skill?