Morpheus MCP Server
Connects AI assistants to HPE Morpheus appliances to manage cloud infrastructure, instances, and multi-tenant environments through natural language. It enables users to provision resources, execute workflows, and perform administrative tasks by translating intent into Morpheus API calls.
README
Morpheus MCP Server
An MCP (Model Context Protocol) server that connects Claude, Ollama, or any AI assistant to a live HPE Morpheus appliance. Speak in plain English — the AI translates your intent into Morpheus API calls and reports back what was done.
What it does
Covers the full Morpheus management lifecycle through natural language:
- Clouds — add, list, sync, and remove cloud integrations (VMware, Proxmox via plugin, AWS, KVM, OpenStack, etc.)
- Groups — create and list Morpheus groups/sites
- Virtual Images — register images from URLs, check status, delete
- Instances — provision, start, stop, restart, delete, and inspect instances
- Instance Discovery — list instance types, layouts, service plans, networks, datastores, resource pools
- Catalog — create and manage catalog item types and blueprints
- Tenants — create, inspect, and delete tenants (sub-accounts)
- Roles — create and manage RBAC roles
- Users — create users under the master tenant or a specific sub-tenant, assign roles
- Workflows and Tasks — list, inspect, and execute workflows on instances
- Process History — view execution history for instances or the appliance
- Release Validation — paste release notes and get an automated API pass/fail test report
Requirements
- Docker and Docker Compose (or Python 3.10+)
- A running HPE Morpheus appliance (version 7.x or 8.x)
- A Morpheus API token with admin or appropriate permissions
- Claude Desktop, Open WebUI (Ollama), or any MCP-compatible client
Setup
Step 1 — Create your config file
cp .env.example .env
Open .env and fill in three values:
MORPHEUS_URL=https://your-morpheus-instance.com
MORPHEUS_API_TOKEN=your-token-here
MORPHEUS_VERSION=8.1.0
How to get your API token: Morpheus UI → top-right user icon → API Access → Generate Token
Step 2 — Start the server
docker compose up --build -d
The server starts on port 8000 (change MCP_PORT in .env if needed).
Check it started correctly:
docker compose logs -f
You should see:
Connected to Morpheus 8.1.0 at https://... | user=admin role=System Admin
Morpheus MCP Server starting on port 8000
SSE endpoint: http://0.0.0.0:8000/sse
Step 3 — Connect your AI client
Claude Desktop
Open the Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add:
{
"mcpServers": {
"morpheus": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"http://localhost:8000/sse"
]
}
},
"preferences": {
"coworkScheduledTasksEnabled": true,
"ccdScheduledTasksEnabled": true,
"coworkWebSearchEnabled": true,
"sidebarMode": "chat"
}
}
Restart Claude Desktop. The morpheus tools appear automatically.
Open WebUI (Ollama)
Settings → Tools → Add Tool Server → URL: http://localhost:8000/sse
Use a model that supports tool calling: llama3.1, qwen2.5, mistral-nemo, or similar.
Example commands
Once connected, talk to the AI naturally:
"Check the Morpheus connection"
"List all configured clouds"
"What cloud types are available on this appliance?"
"Add a VMware cloud using vCenter at https://vcenter.lab/sdk"
"List all instance types"
"What service plans are available for VMware?"
"Provision a test VM called demo-01 on the VMware cloud"
"Show me all running instances"
"Stop instance 42"
"Create a tenant called Acme Corp"
"Add a read-only role and create a user under Acme Corp"
"List all workflows"
"Run workflow 5 on instance 12"
"Validate this release: [paste Morpheus release notes here]"
Switching Morpheus instances
Update .env with the new URL and token, then restart:
docker compose down
# edit .env
docker compose up -d
Running without Docker
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
cp .env.example .env # fill in your values
python server.py
Proxmox note
Proxmox is not a built-in Morpheus cloud type. It requires the community plugin to be installed first:
- Download the plugin JAR from the HPE Morpheus Proxmox VE Plugin repository
- Install it in Morpheus: Administration → Integrations → Plugins → Upload File
- Once installed, run
list_zone_types— the Proxmox code will appear - Use that code with
add_cloudto register your Proxmox host
SSL certificates
Self-signed certificates are handled by default (MORPHEUS_VERIFY_SSL=false in .env). For production appliances with valid certificates, set MORPHEUS_VERIFY_SSL=true.
Moving to Proxmox or another host
Copy the project folder to the target machine, install Docker, and run the same docker compose up command. The .env file is the only thing that needs to change per environment.
Available Tools Reference
| Tool | Description |
|---|---|
check_connection |
Verify connectivity and display current user |
list_zone_types |
List all available cloud type codes |
list_clouds |
List all configured clouds |
get_cloud |
Get cloud details by ID |
add_vmware_cloud |
Add a VMware vCenter cloud |
add_cloud |
Add any cloud by zone type code |
sync_cloud |
Trigger manual cloud sync |
delete_cloud |
Remove a cloud integration |
list_groups |
List groups/sites |
create_group |
Create a new group |
list_virtual_images |
List registered virtual images |
get_virtual_image |
Get image details and status |
register_image_from_url |
Register an image from a URL |
delete_virtual_image |
Remove a virtual image |
list_instance_types |
List available instance types |
get_instance_type_layouts |
List layouts for an instance type |
list_service_plans |
List CPU/RAM/disk plans |
list_networks |
List available networks |
list_datastores |
List datastores for a cloud |
list_resource_pools |
List resource pools for a cloud |
list_instances |
List instances with optional filters |
get_instance |
Get instance details and IP |
provision_instance |
Provision a new instance |
stop_instance |
Stop a running instance |
start_instance |
Start a stopped instance |
restart_instance |
Restart an instance |
delete_instance |
Deprovision an instance |
list_catalog_items |
List catalog item types |
get_catalog_item |
Get catalog item details |
create_catalog_item |
Create a catalog item |
delete_catalog_item |
Delete a catalog item |
list_blueprints |
List blueprints |
get_blueprint |
Get blueprint details |
create_blueprint |
Create a new blueprint |
delete_blueprint |
Delete a blueprint |
list_tenants |
List all tenants |
get_tenant |
Get tenant details |
create_tenant |
Create a sub-tenant |
delete_tenant |
Delete a tenant |
list_roles |
List all roles |
get_role |
Get role details |
create_role |
Create a new role |
delete_role |
Delete a role |
list_users |
List users (global or per-tenant) |
get_user |
Get user details |
create_user |
Create a user with role assignment |
delete_user |
Delete a user |
list_workflows |
List workflows/task sets |
get_workflow |
Get workflow details and tasks |
run_workflow_on_instance |
Execute a workflow on an instance |
list_tasks |
List tasks |
list_processes |
View execution history |
validate_release |
Parse release notes and run API tests |
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。