mcp-creator is a conversational tool that guides developers through creating, building, and publishing Python MCP servers to PyPI and the MCP Marketplace — all from within an AI assistant.
Profile management: Persist your setup status, GitHub/PyPI usernames, and project history across sessions so you never repeat onboarding.
Environment checking: Detect whether required tools are installed (uv, git, gh CLI, PyPI token) and walk you through any missing steps.
PyPI name availability: Verify your desired package name is free on PyPI before scaffolding.
Project scaffolding: Generate a fully structured, immediately runnable MCP server from a name, description, and tool definitions — with support for paid/gated tools, environment variables, and remote (SSE/HTTP + Dockerfile) or local (stdio) hosting.
Add tools to existing projects: Extend a scaffolded server with new tool modules, service stubs, and tests without rebuilding from scratch.
Build & publish: Run uv build to produce distributable artifacts and uv publish to push your package live to PyPI.
GitHub integration: Initialize git, create a GitHub repo via the gh CLI, and push your project code.
Marketplace submission: Generate a LAUNCHGUIDE.md file formatted for MCP Marketplace submission, including tagline, features, tags, tools summary, and category.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-creator Help me build an MCP server that searches Spotify playlists."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
pip install mcp-creatorRelated MCP server: Vibe Coder MCP
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": []
}
}
}Tool | What it does |
| Load your persistent profile — setup status, project history. Called first every session. |
| Save setup state, usernames, and project history across sessions |
| Detect what's installed (uv, git, gh, PyPI token) — only walks through missing steps |
| Check if a package name is available on PyPI |
| Create a complete MCP server project from a name + description + tool definitions |
| Add a new tool to an existing scaffolded project |
| Run |
| Run |
| Initialize git, create a GitHub repo, and push the code |
| Create LAUNCHGUIDE.md for marketplace submission |
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.
Tell your AI what you want to build: "I want an MCP server that checks the weather"
It checks the name: calls check_pypi_name to verify availability on PyPI
It scaffolds the project: calls scaffold_server with 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_github creates a repo and pushes your code
Submit to marketplace: generate_launchguide creates the submission file with your repo URL
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.pyThe generated server runs immediately — stub services return placeholder data so you can test before implementing real logic.
Python 3.11+
uv (for building and publishing)
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 -vUnclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for generating rough-draft project plans from natural-language prompts.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gmoneyn/mcp-creator'
If you have feedback or need assistance with the MCP directory API, please join our Discord server