README.md
Create, build, and publish Python MCP servers to PyPI — conversationally.
mcp-creator
Create, build, and publish Python MCP servers to PyPI — conversationally.
Install mcp-creator, add it to your AI assistant, and it walks you through the entire process: naming your package, scaffolding a complete project, building, and publishing to PyPI.
Install
pip install mcp-creator
Setup
Add to Claude Code (~/.claude/settings.json):
{
"mcpServers": {
"mcp-creator": {
"command": "mcp-creator",
"args": []
}
}
}
Or for Cursor (.cursor/mcp.json):
{
"mcpServers": {
"mcp-creator": {
"command": "mcp-creator",
"args": []
}
}
}
Tools
| Tool | What it does |
|---|---|
get_creator_profile |
Load your persistent profile — setup status, project history. Called first every session. |
update_creator_profile |
Save setup state, usernames, and project history across sessions |
check_setup |
Detect what's installed (uv, git, gh, PyPI token) — only walks through missing steps |
check_pypi_name |
Check if a package name is available on PyPI |
scaffold_server |
Create a complete MCP server project from a name + description + tool definitions |
add_tool |
Add a new tool to an existing scaffolded project |
build_package |
Run uv build on the project |
publish_package |
Run uv publish to PyPI |
setup_github |
Initialize git, create a GitHub repo, and push the code |
generate_launchguide |
Create LAUNCHGUIDE.md for marketplace submission |
Publish to MCP Marketplace
Once your server is on PyPI, list it on MCP Marketplace to reach thousands of AI users:
- Security scanning — every submission is automatically scanned, and the score is shown to users
- One-click install — users add your server to Claude, Cursor, or any MCP client in one click
- Built-in payments — set a price (one-time or subscription), connect Stripe, and keep 85% of every sale
- Creator dashboard — track installs, revenue, reviews, and license keys
Run generate_launchguide after publishing to create your submission file, then submit at mcp-marketplace.io/submit.
How It Works
- Tell your AI what you want to build: "I want an MCP server that checks the weather"
- It checks the name: calls
check_pypi_nameto verify availability on PyPI - It scaffolds the project: calls
scaffold_serverwith your tool definitions — generates a complete, runnable project - You fill in the logic: replace the TODO stubs in
services/with your real API calls - Build & publish:
build_package→publish_package→ live on PyPI - Push to GitHub:
setup_githubcreates a repo and pushes your code - Submit to marketplace:
generate_launchguidecreates the submission file with your repo URL
What Gets Generated
For a project named my-weather-mcp with a get_weather tool:
my-weather-mcp/
├── pyproject.toml ← hatchling build, mcp[cli] dep, CLI entry point
├── README.md ← install instructions + MCP config JSON
├── .gitignore
├── src/my_weather_mcp/
│ ├── __init__.py
│ ├── server.py ← FastMCP + @mcp.tool() for each tool
│ ├── transport.py
│ ├── tools/
│ │ ├── __init__.py
│ │ └── get_weather.py
│ └── services/
│ ├── __init__.py
│ └── get_weather_service.py ← TODO: your logic here
└── tests/
├── test_server.py
└── test_get_weather.py
The generated server runs immediately — stub services return placeholder data so you can test before implementing real logic.
Requirements
- Python 3.11+
- uv (for building and publishing)
Development
git clone https://github.com/gmoneyn/mcp-creator.git
cd mcp-creator
uv venv .venv && source .venv/bin/activate
uv pip install -e ".[dev]"
pytest -v
Tools (10)
get_creator_profileLoad your persistent profile including setup status and project history.update_creator_profileSave setup state, usernames, and project history across sessions.check_setupDetect installed dependencies like uv, git, gh, and PyPI tokens.check_pypi_nameCheck if a package name is available on PyPI.scaffold_serverCreate a complete MCP server project from a name, description, and tool definitions.add_toolAdd a new tool to an existing scaffolded project.build_packageRun uv build on the project.publish_packageRun uv publish to PyPI.setup_githubInitialize git, create a GitHub repo, and push the code.generate_launchguideCreate LAUNCHGUIDE.md for marketplace submission.Configuration
claude_desktop_config.json
{"mcpServers": {"mcp-creator": {"command": "mcp-creator", "args": []}}}Try it
→I want to build an MCP server that checks the weather, can you help me scaffold it?
→Check if the package name 'weather-mcp-service' is available on PyPI.
→Add a new tool called 'get_forecast' to my current project.
→Build my project and publish it to PyPI.
→Initialize a GitHub repository for my current MCP project and push the code.