Cookiecutter
Cookiecutter template for MCP server development with FastMCP
What is Cookiecutter?
Cookiecutter is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to cookiecutter template for mcp server development with fastmcp
Cookiecutter template for MCP server development with FastMCP
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Cookiecutter template for MCP server development with FastMC
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx cookiecutterConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cookiecutter
MCP Server Cookiecutter is a project template generator for building FastMCP-based MCP servers. Developed by the BioContextAI team for biomedical AI use cases, it scaffolds a complete, publishable Python package with FastMCP wiring, GitHub Actions for PyPI releases, and a standardized structure — letting developers go from zero to a working MCP server in minutes.
Prerequisites
- Python 3.9 or higher with pip or uv installed
- cookiecutter installed (pip install cookiecutter or available via uvx)
- Git for version control of the generated project
- A PyPI account if you intend to publish the generated server
Install cookiecutter
Install cookiecutter globally so you can run it from anywhere, or use uvx for a one-off invocation.
pip install --user cookiecutter
# Or with uv (no install needed):
uvx cookiecutter https://github.com/biocontext-ai/mcp-server-cookiecutter.gitGenerate a new MCP server project
Run cookiecutter against the template repository. You will be prompted for project name, package name, author, and other metadata.
cookiecutter https://github.com/biocontext-ai/mcp-server-cookiecutter.gitEnter the generated project and install dependencies
Navigate into the newly created directory and install it in editable mode with uv so you can develop and test locally.
cd your-project-name
uv pip install -e .
# Or with pip:
pip install -e .Add your MCP tools to the server
Open the main server Python file and implement your FastMCP tools using the @mcp.tool() decorator pattern that the template provides.
# Example tool in your generated server file:
from fastmcp import FastMCP
mcp = FastMCP("your-server-name")
@mcp.tool()
def my_tool(input: str) -> str:
"""Describe what this tool does."""
return f"Result: {input}"
if __name__ == "__main__":
mcp.run()Configure your MCP client to use the new server
Wire the generated server into your MCP client configuration for local testing before publishing to PyPI.
{
"mcpServers": {
"your-server-name": {
"command": "uvx",
"args": ["your_package_name"],
"env": {
"UV_PYTHON": "3.12"
}
}
}
}Publish to PyPI (optional)
The template includes a GitHub Actions release.yaml workflow. Tag a release on GitHub and the workflow will build and publish your package to PyPI automatically.
git tag v0.1.0
git push origin v0.1.0Cookiecutter Examples
Client configuration
Example claude_desktop_config.json for a server generated from this cookiecutter template, once published to PyPI.
{
"mcpServers": {
"my-bio-server": {
"command": "uvx",
"args": ["my-bio-server"],
"env": {
"UV_PYTHON": "3.12"
}
}
}
}Prompts to try
Example prompts relevant to a biomedical MCP server built with this template.
- "Generate a new MCP server project named 'pubmed-search' using the biocontext-ai cookiecutter template."
- "Add a tool to my MCP server that fetches abstracts from PubMed given a search query."
- "Show me the FastMCP tool structure so I can add a new endpoint to my generated server."
- "Help me write the GitHub Actions release workflow to publish my MCP server to PyPI."Troubleshooting Cookiecutter
cookiecutter prompts are missing or the template fails to render
Ensure you have cookiecutter 2.x installed (pip install --upgrade cookiecutter). If using uvx, run the full command: uvx cookiecutter https://github.com/biocontext-ai/mcp-server-cookiecutter.git
Generated server fails to start with FastMCP import error
Install FastMCP in your project environment: pip install fastmcp or uv pip install fastmcp. The template lists it as a dependency but it must be installed in the same environment you run the server from.
PyPI publish fails in GitHub Actions
Add your PyPI API token as a GitHub Actions secret named PYPI_API_TOKEN in your repository settings (Settings → Secrets → Actions). The included release.yaml workflow expects this secret name.
Frequently Asked Questions about Cookiecutter
What is Cookiecutter?
Cookiecutter is a Model Context Protocol (MCP) server that cookiecutter template for mcp server development with fastmcp It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cookiecutter?
Follow the installation instructions on the Cookiecutter GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Cookiecutter?
Cookiecutter works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cookiecutter free to use?
Yes, Cookiecutter is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Cookiecutter Alternatives — Similar Developer Tools Servers
Looking for alternatives to Cookiecutter? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cookiecutter in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cookiecutter?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.