python-openstackmcp-server is an OpenStack MCP server, with the full name OpenStack Model Context Protocol Server. It is a project based on openstacksdk that, by implementing the Model Context Protocol (MCP) protocol, provides AI assistants with an interface for interacting with OpenStack services.
Main capabilities This project provides the following types of tool capabilities:
Compute Tools: Manage OpenStack compute resources, including servers and flavors. Image Tools: Manage OpenStack images. Identity Tools: Handle OpenStack identity authentication-related operations. Network Tools: Manage OpenStack network resources. Block Storage Tools: Manage OpenStack block storage resources.
Usage (quick start based on Claude Desktop) Using this server requires meeting the following prerequisites:
- Python 3.10 or later.
- OpenStack credentials configured in the clouds.yaml file.
- Claude Desktop installed.
Configuration steps:
-
Create or update the clouds.yaml file and fill in the OpenStack credentials. An example clouds.yaml content is as follows: clouds: openstack: auth: auth_url: https://your-openstack-auth-url.com username: your-username password: your-password project_name: your-project-name user_domain_name: Default project_domain_name: Default region_name: your-region interface: public identity_api_version: 3
-
Create or update the Claude Desktop configuration file. The configuration file paths on different systems are as follows:
- macOS: edit $HOME/Library/Application Support/Claude/claude_desktop_config.json
- Windows: edit %APPDATA%\Claude\claude_desktop_config.json
- Linux: edit $HOME/.config/Claude/claude_desktop_config.json
Development and testing This project supports both uv and tox for development and testing:
- Use uv (fast local development).
- Use tox (the standard OpenStack way).
The project includes comprehensive test coverage, with coverage above 85%, and the test files are located in the tests/ directory.
Applicable scenarios This server is suitable for scenarios where users want to manage OpenStack cloud infrastructure through an AI assistant (such as Claude Desktop), including operations such as managing compute resources, images, identity authentication, network resources, and block storage resources.
Limitations and notes The current materials do not provide more details such as specific installation commands, pricing, or platform support scope. Before use, an available OpenStack environment and credentials are required. The project welcomes contributions; for details, see the CONTRIBUTING file. The project uses the Apache License 2.0; for details, see the LICENSE file.
