About AI-Create-MCP (WIP)
AI-Create-MCP is a Go command-line tool that generates an MCP project from an OpenAPI Specification file. It is intended for developers and supports project settings plus optional Inspector and Claude.app integration; the project is marked as a work in progress.
Key features
- 01Generate MCP projects from OAS files
- 02Set project name, directory, and version
- 03Optional Inspector integration
- 04Optional Claude.app integration
- 05Automate confirmation prompts
Use cases
- 01Scaffold an MCP server from an OpenAPI definition
- 02Set up a named project with a chosen version
- 03Generate a project without interactive prompts
MCP support
It converts OAS files into MCP programs. The generated MCP server can be configured with optional Inspector and Claude.app integration.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAI-Create-MCP (WIP)
This project is a work in progress and not yet complete.
ai-create-mcp is a Go-based tool that converts OpenAPI Specification (OAS) files into a Model Context Protocol (MCP) program. It provides a simple and efficient way to generate MCP-compliant code or configurations from OAS files, with customizable options for project setup and integrations.
Features
- Convert OAS files to MCP protocol.
- Customizable project name, directory, and version.
- Optional integration with Claude.app.
- Inspector tool for debugging and analysis.
Installation
To install the ai-create-mcp, ensure you have Go installed on your system. Then, run the following command:
go install github.com/xxlv/ai-create-mcp
Alternatively, clone the repository and build it manually:
git clone https://github.com/xxlv/ai-create-mcp.git
cd ai-create-mcp
go build
Usage
The tool is configured via command-line flags. Below is the list of available flags and their descriptions:
| Flag | Type | Default Value | Description |
|---|---|---|---|
-path | string | "" | Directory to create the project in |
-name | string | "" | Project name |
-oaspath | string | "" | Path to the OAS file |
-version | string | "0.1.0" | Server version |
-inspector | bool | true | Enable/disable the inspector tool |
-description | string | "Simple mcp" | Project description |
-claudeapp | bool | true | Enable/disable Claude.app integration |
-autoyes | bool | true | Enable/disable auto-confirmation |
Example
To generate an MCP project from an OAS file, run:
ai-create-mcp -path ./myproject -name my-mcp-app -oaspath ./openapi.yaml -version 1.0.0
This command will:
- Create a project in the
./myprojectdirectory. - Name the project
my-mcp-app. - Use the OAS file located at
./openapi.yaml. - Set the server version to
1.0.0.
./testdata/openapi.ymlwill be converted into the following tools🔧

To disable the inspector and Claude.app integration, use:
ai-create-mcp -path ./myproject -name my-mcp-app -oaspath ./openapi.yaml -inspector=false -claudeapp=false
For a fully automated run (no prompts), enable -autoyes:
ai-create-mcp -path ./myproject -name my-mcp-app -oaspath ./openapi.yaml -autoyes
Configuration
The tool relies on the provided command-line flags for configuration. Ensure that:
- The
-oaspathpoints to a valid OAS file (e.g.,.yaml). - The
-pathdirectory is writable. - The
-nameadheres to valid naming conventions for your use case.
Contributing
Contributions are welcome! To contribute:
- Fork the repository.
- Create a new branch (
git checkout -b feature/your-feature). - Make your changes and commit them (
git commit -m "Add your feature"). - Push to the branch (
git push origin feature/your-feature). - Open a pull request.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Contact
For questions or support, please open an issue on the GitHub repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.