MCP Scaffold

What it does

When your agent uses it

• Creating new MCP servers
• Initializing MCP projects
• Generating server boilerplate
• Setting up MCP development environments

Example prompts

• “/mcp-scaffold”

Requirements

• Python 3
• Docker

Workflow steps

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

1. 1Scaffold - Generate project structure
2. 2Customize - Add your tools, resources, prompts
3. 3Validate - Check for common issues
4. 4Test - Run locally with python server.py
5. 5Deploy - Add to Claude Code with claude mcp add

What it can do on your machine

Read from SKILL.md and the folder at commit cb80eae. 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 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • 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 no API keys, tokens, secrets or passwords.

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

Context cost

MCP Scaffold loads about 940 tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 184 words of instructions outside code blocks.

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

~84

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

~940

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

~6.6k

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 timothywarner-org/claude-code at commit cb80eae, republished under its MIT licence (© timothywarner-org). 184 words, ~940 tokens.

name

mcp-scaffold

description

Scaffold production-ready Python MCP servers using FastMCP. Use when creating new MCP servers, initializing MCP projects, generating server boilerplate, or setting up MCP development environments. Supports all MCP primitives (tools, resources, prompts) with Pydantic validation, async patterns, and proper project structure.

python scripts/scaffold.py my-server --output ./my-server

python scripts/scaffold.py my-server --template basic

python scripts/scaffold.py my-server --template full

python scripts/scaffold.py my-server \
  --tools \
  --resources \
  --prompts \
  --lifespan \
  --output ./servers/my-server

python scripts/validate.py path/to/server.py

my-server/
├── server.py           # Main MCP server
├── requirements.txt    # Python dependencies
├── README.md          # Usage documentation
└── data/              # Default data directory (gitignored)

from fastmcp import FastMCP

mcp = FastMCP("my-server")

@mcp.tool
def hello(name: str) -> str:
    """Greet someone by name."""
    return f"Hello, {name}!"

if __name__ == "__main__":
    mcp.run()

from pydantic import Field

@mcp.tool
def my_tool(
    param: str = Field(description="Parameter description"),
    optional: int = Field(default=10, description="Optional with default")
) -> dict:
    """Tool description shown to LLM."""
    return {"result": param}

@mcp.resource("myscheme://path/to/resource")
def static_resource() -> str:
    """Resource description."""
    return json.dumps({"data": "value"})

@mcp.resource("myscheme://items/{item_id}")
def dynamic_resource(item_id: str) -> str:
    """Dynamic resource with URI template."""
    return json.dumps({"id": item_id})

@mcp.prompt(name="my_prompt", tags={"category"})
def my_prompt(
    topic: str = Field(description="What to analyze")
) -> str:
    """Prompt description."""
    return f"Please analyze {topic} and provide insights."

© timothywarner-org, 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 10 other files (scripts, references, assets) in .claude/skills/mcp-scaffold of timothywarner-org/claude-code.

• SKILL.md
• assets/templates/README.md
• assets/templates/basic-server.py
• assets/templates/full-server.py
• assets/templates/requirements.txt
• references/DEPLOYMENT.md
• references/FASTMCP-GUIDE.md
• references/PATTERNS.md
• scripts/init_project.py
• scripts/scaffold.py
• scripts/validate.py

Open the folder on GitHubat commit cb80eae