create_mcp_serverLABSCO SUMMARY
Templates carry the boring correctness; guidance covers the rest.
Most of what makes a new MCP server tedious is structural — process cleanup, error boundaries, logging to stderr rather than stdout — and a template gets that right without anyone thinking about it. The guidance tools cover the part a template cannot, which is the decision about what your server should expose in the first place. Saved workflows are worth using if you generate servers of a similar shape repeatedly.
What it is
A server for building servers. It generates a new MCP server project from a name, a description and a feature list, using a library of templates; alongside that it answers design questions with topic-specific guidance, and can save a multi-step creation process as a reusable workflow.
What you get
create_mcp_servergenerates the project fromname,description,language,template_typeand afeatureslist such as tools and resourceslist_templatesshows what is available, filterable by languageget_ai_guidanceanswers bytopicandserver_type— asking for security guidance on a database server returns advice shaped for that casesave_workflowrecords an ordered set of steps, mixing input collection, guidance and generation, so the same process can be repeated- A template library covering a plain Python server, one with resources for database and API integration, one using sampling, and a Gradio interface
- Templates are Jinja2 files with a metadata descriptor, so adding your own is a directory and two files
- A Gradio web interface for managing servers visually, as an alternative to driving it through a client
Requirements
Python 3.10 or higher and the uv package manager. Clone the repository, create the environment and copy the example environment file; the client's uv launch installs the dependencies from pyproject.toml on first run. AI guidance needs at least one model provider configured — ANTHROPIC_API_KEY, OPENAI_API_KEY or a local OLLAMA_BASE_URL. DEFAULT_OUTPUT_DIR decides where generated servers land, and GRADIO_SERVER_PORT controls the web interface. The client launches it through uv against the repository directory.
Setup effort
Build from source — git clone https://github.com/angrysky56/mcp-creator-mcp.git
USE CASES
01
Starting a new server without copying an old one
Describe what it should do and get a structured project in the language you asked for.
02
Picking the right starting point
List the templates for your language and see which one matches the features you need.
03
Getting design advice specific to what you are building
Ask about a topic for your kind of server rather than reading generic protocol docs.
04
Repeating a build process across projects
Save the sequence of requirements gathering, review and generation, and run it again next time.
4 tools
Listed in project docs. Your client may show a different list.
list_templatesget_ai_guidancesave_workflowBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- Python 3.10 or higher
- uv package manager
- One AI model provider for AI guidance: ANTHROPIC_API_KEY, OPENAI_API_KEY or a local OLLAMA_BASE_URL
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/angrysky56/mcp-creator-mcp.git
cd mcp-creator-mcp
uv venv --python 3.12 --seed
source .venv/bin/activate
cp .env.example .env # then add your API keysMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"mcp-creator": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_MCP_CREATOR_MCP>",
"run",
"python",
"main.py"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>"
}
}
}
}AI guidance needs only one model provider, and this block sets ANTHROPIC_API_KEY. To use OpenAI instead, put OPENAI_API_KEY in the block's "env" section in its place, or OLLAMA_BASE_URL for a local Ollama.
