greenlake-users-mcp
Advanced tools
HPE GreenLake users MCP Server provides read-only access to the HPE GreenLake users APIs through the Model Context Protocol.
This MCP server enables AI assistants and development tools to interact with HPE GreenLake users programmatically. It follows the standardized MCP server architecture with shared authentication components and HTTP client adapters.
From PyPI (recommended):
pip install greenlake-users-mcp
After installation, run the server with:
python -m greenlake_users_mcp
Set the following environment variables:
| Variable | Required | Description | Example |
|---|---|---|---|
GREENLAKE_API_BASE_URL | Yes | Base URL for GreenLake APIs | https://global.api.greenlake.hpe.com |
GREENLAKE_CLIENT_ID | Yes | OAuth2 client ID | your-client-id |
GREENLAKE_CLIENT_SECRET | Yes | OAuth2 client secret | your-client-secret |
GREENLAKE_WORKSPACE_ID | Yes | Workspace identifier (token issuer auto-generated from this) | your-workspace-id |
MCP_TOOL_MODE | No | Tool operation mode (see Tool Modes section) | static (default) or dynamic |
GREENLAKE_LOG_LEVEL | No | Logging level for stderr output | ERROR (default), WARNING, INFO, DEBUG |
GREENLAKE_FILE_LOGGING | No | Enable file logging to disk | false (default) or true |
This MCP server uses loguru for structured logging with strict MCP protocol compliance.
stderr (Default):
GREENLAKE_LOG_LEVEL (default: ERROR)File logging (Optional):
GREENLAKE_FILE_LOGGING=true~/.hpe/mcp-logs/users/users-mcp.logProduction (minimal logging):
export GREENLAKE_LOG_LEVEL=ERROR
# File logging disabled by default
Development (verbose logging):
export GREENLAKE_LOG_LEVEL=DEBUG
export GREENLAKE_FILE_LOGGING=true
Debugging specific issues:
export GREENLAKE_LOG_LEVEL=INFO
export GREENLAKE_FILE_LOGGING=true
# Check logs at: ~/.hpe/mcp-logs/users/
The server automatically filters noisy third-party library logs:
httpx, httpcore, urllib3, asyncio are limited to WARNING level and aboveThis MCP server supports two different tool operation modes that can be switched at runtime:
Tools available in dynamic mode:
list_endpoints - Discover available API endpoints with optional filteringget_endpoint_schema - Get detailed schema information for specific endpointsinvoke_dynamic_tool - Execute API calls with runtime parameter validationConfigure the MCP_TOOL_MODE environment variable in your MCP client configuration:
{
"servers": {
"users": {
"env": {
"MCP_TOOL_MODE": "static" // or "dynamic"
}
}
}
}
static - Individual tools per endpoint (default)dynamic - 3 generic meta-tools for all endpointsAdd to your .vscode/mcp.json:
Using PyPI package:
{
"servers": {
"users": {
"type": "stdio",
"command": "python",
"args": ["-m", "greenlake_users_mcp"],
"env": {
"GREENLAKE_API_BASE_URL": "https://global.api.greenlake.hpe.com",
"GREENLAKE_CLIENT_ID": "your-client-id",
"GREENLAKE_CLIENT_SECRET": "your-client-secret",
"GREENLAKE_WORKSPACE_ID": "your-workspace-id",
"MCP_TOOL_MODE": "static",
"GREENLAKE_LOG_LEVEL": "INFO",
"GREENLAKE_FILE_LOGGING": "false"
}
}
}
}
Add to your claude_desktop_config.json:
Using PyPI package:
{
"mcpServers": {
"users": {
"command": "python",
"args": ["-m", "greenlake_users_mcp"],
"env": {
"GREENLAKE_API_BASE_URL": "https://global.api.greenlake.hpe.com",
"GREENLAKE_CLIENT_ID": "your-client-id",
"GREENLAKE_CLIENT_SECRET": "your-client-secret",
"GREENLAKE_WORKSPACE_ID": "your-workspace-id",
"MCP_TOOL_MODE": "static",
"GREENLAKE_LOG_LEVEL": "INFO",
"GREENLAKE_FILE_LOGGING": "false"
}
}
}
}
This server provides the following MCP tools:
Description: Retrieve list of users with filtering, and pagination options. All users are returned when no filters are provided.
Note: User view all permission is required to invoke this API.
Rate limit: 300 requests per minute per workspace, resulting in a 429 error if exceeded.
Method: GET /identity/v1/users
Parameters:
filter (str, optional):id: string (uuid) - username: string (email) - userStatus: string - createdAt: string (date-time) - updatedAt: string (date-time) - lastLogin: string (date-time)offset (int, optional):limit (int, optional):Description: Retrieve a single user based on a given user ID.
Method: GET /identity/v1/users/{id}
Parameters:
id (str, required):Example: 7600415a-8876-5722-9f3c-b0fd11112283
This MCP server enables AI assistants to answer natural language questions about your HPE GreenLake users resources. Here are some example queries you can try:
User Management:
These are just examples - you can ask questions in your own words, and the AI assistant will use the appropriate MCP tools to retrieve the information from HPE GreenLake.
This MCP server implements read-only access to the following users API endpoints:
GET /identity/v1/users - Retrieve list of users with filtering, and pagination options. All users are returned when no filters are provided.
Note: User view all permission is required to invoke this API.
Rate limit: 300 requests per minute per workspace, resulting in a 429 error if exceeded.
GET /identity/v1/users/{id} - Retrieve a single user based on a given user ID.
make help # Show available commands
make install # Install dependencies
make test # Run tests
make clean # Clean build artifacts
users/
├── pyproject.toml # Dependencies and configuration
├── README.md # This file
├── Makefile # Development commands
├── greenlake_users_mcp/ # Python package
│ ├── __init__.py
│ ├── __main__.py # Entry point
│ ├── _version.py # Version constants
│ ├── auth/ # Authentication components
│ │ ├── __init__.py
│ │ ├── oauth2_provider.py # OAuth2 client credentials
│ │ └── token_manager.py # Token lifecycle management
│ ├── config/ # Configuration management
│ │ ├── __init__.py
│ │ ├── logging.py # Logging configuration
│ │ └── settings.py # Application settings
│ ├── models/ # Data models
│ │ ├── __init__.py
│ │ └── base.py # Base model classes
│ ├── server/ # MCP server implementation
│ │ ├── __init__.py
│ │ ├── app.py # Application factory
│ │ ├── fastmcp_instance.py # FastMCP singleton
│ │ └── mcp_server.py # MCP server core
│ ├── tools/ # MCP tools
│ │ ├── __init__.py
│ │ ├── base.py # Base tool class
│ │ ├── registry.py # Tool registration
│ │ └── implementations/
│ │ └── *.py # Tool implementations
│ └── utils/ # Utility modules
│ ├── __init__.py
│ └── http_client.py # HTTP client utilities
└── tests/ # Test suite
├── conftest.py # Shared fixtures
├── shared/
│ └── http.py # Testing helpers
├── unit/
│ └── test_*.py # Unit tests
└── integration/
└── test_live_tools.py
tools/implementations/BaseTool and implement required methodstools/registry.pytests/The test suite reads credentials from environment variables. Export the following variables before running integration tests:
export GREENLAKE_CLIENT_ID=your-client-id
export GREENLAKE_CLIENT_SECRET=your-client-secret
export GREENLAKE_WORKSPACE_ID=your-workspace-id
export GREENLAKE_API_BASE_URL=https://global.api.greenlake.hpe.com
Run the full test suite (unit + integration when credentials are present):
make test
Run unit-only checks:
make test-unit
Integration smoke tests require the variables above plus any tool arguments (MCP_TEST_USERS_<PARAM_NAME>):
make test-integration
The generated suite provides:
Server won't start:
Verify environment variables are set
Check that the package is installed: pip show greenlake-users-mcp
Review log output for specific errors
Authentication failures:
Tool execution errors:
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
FAQs
HPE GreenLake users MCP Server
We found that greenlake-users-mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 2 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
A misconfiguration gave three Anthropic models internet access, and one, believing it was in a simulation, shipped a credential-stealing package to PyPI.
Security News
/Company News
Socket has joined the new Composer and Packagist sponsorship program as a launch sponsor, supporting the team that keeps PHP's package ecosystem secure.
Research
/Security News
Benign-looking npm packages split malicious functionality across a dependency chain that deploys a cross-platform RAT targeting Alibaba developers.