Create MCP Servers

What it does

When your agent uses it

• Building custom integrations
• Any server that Claude should interact with via the MCP protocol

Example prompts

• “/create-mcp-servers”

Requirements

• Python 3
• A Bash shell
• A credential in API_KEY
• A credential in MY_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Never Hardcode Secrets - Use ${VAR} expansion in configs, environment variables in code
2. 2Use cwd Property - Isolates dependencies (not --cwd in args)
3. 3Always Absolute Paths - which uv to find paths, never relative
4. 4One Server Per Directory - ~/Developer/mcp/{server-name}/
5. 5Use uv for Python - Better than pip, handles venvs automatically

What it can do on your machine

Read from SKILL.md and the folder at commit 1757615. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Shell, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • claude

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Create MCP Servers loads about 1.5k tokens when it runs, and up to ~56k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 498 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~74

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~56k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from glittercowboy/taches-cc-resources at commit 1757615, republished under its MIT licence (© glittercowboy). 498 words, ~1,454 tokens.

name

create-mcp-servers

description

Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript and Python implementations.

<objective>
MCP servers extend Claude's capabilities by exposing tools, resources, and prompts. This skill guides creation of production-ready MCP servers with API integrations, OAuth authentication, response optimization, and proper installation in Claude Code and Claude Desktop.
</objective>

<context>
MCP servers expose:
- **Tools**: Functions Claude can call (API requests, file operations, calculations)
- **Resources**: Data Claude can read (files, database records, API responses)
- **Prompts**: Reusable prompt templates with arguments

<routing>
Based on user intent, route to appropriate workflow:

# List servers
claude mcp list

# Add server (Python)
claude mcp add --transport stdio <name> \
  --env API_KEY='${API_KEY}' \
  -- uv --directory ~/Developer/mcp/<name> run python -m src.server

# Add server (TypeScript)
claude mcp add --transport stdio <name> \
  --env API_KEY='${API_KEY}' \
  -- node ~/Developer/mcp/<name>/build/index.js

# Remove server
claude mcp remove <name>

# Check logs
tail -f ~/Library/Logs/Claude/mcp-server-<name>.log

# Find paths
which uv && which node && which python

echo $MY_API_KEY  # Check if set
echo 'export MY_API_KEY="value"' >> ~/.zshrc && source ~/.zshrc

© glittercowboy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 23 other files (scripts, references) in skills/create-mcp-servers of glittercowboy/taches-cc-resources.

• SKILL.md
• references/adaptive-questioning-guide.md
• references/api-research-template.md
• references/auto-installation.md
• references/best-practices.md
• references/creation-workflow.md
• references/large-api-pattern.md
• references/oauth-implementation.md
• references/python-implementation.md
• references/response-optimization.md
• references/testing-and-deployment.md
• references/tools-and-resources.md
• references/traditional-pattern.md
• references/typescript-implementation.md
• references/validation-checkpoints.md
• scripts/setup-python-project.sh
• scripts/setup-typescript-project.sh
• templates/operations.json
• … and 6 more

Open the folder on GitHubat commit 1757615