MegaCloud MCP Server
Enables middleware management, information checking, backups, and node-level operations for the MegaCloud API.
README
MegaCloud MCP Server
MCP Server for the MegaCloud API, enabling middleware management, information checking, and more.
Features
- Host checking
- Middleware lifecycle (create, start, stop, restart, delete, add node, delete node)
- Status and configuration inspection
- Backups
- Node-level management
Tools
Below is the list of your MCP tools converted into the requested format:
-
list_available_hosts- List all available hosts that can be used to deploy middleware.
- Inputs: None
- Returns: List of host objects.
-
list_middleware_types- List all middleware types.
- Inputs: None
- Returns: List of supported middleware‐type identifiers.
-
list_middleware_instances- List all middleware instances that are currently deployed.
- Inputs: None
- Returns: List of middleware instance objects
-
restart_middleware- Restart a middleware instance.
- Inputs:
middleware_instance_name(string): Middleware Instance Name
- Returns: Operation result / status confirmation
-
stop_middleware- Stop a middleware instance.
- Inputs:
middleware_instance_name(string): Middleware Instance Name
- Returns: Operation result / status confirmation
-
start_middleware- Start a middleware instance.
- Inputs:
middleware_instance_name(string): Middleware Instance Name
- Returns: Operation result / status confirmation
-
delete_middleware- Delete a middleware instance.
- Inputs:
middleware_instance_name(string): Middleware Instance Name
- Returns: Operation result / deletion confirmation
-
get_middleware_info- Get all information of a middleware instance, like configs, nodes, etc.
- Inputs:
middleware_instance_name(string): Middleware Instance Name
- Returns: Detailed middleware-instance object
-
get_middleware_status- Get the status of a middleware instance.
- Inputs:
middleware_instance_name(string): Middleware Instance Name
- Returns: Status object (e.g. running/stopped + node list)
-
backup_middleware- Backup a middleware instance.
- Inputs:
middleware_instance_name(string): Middleware Instance Name
- Returns: Backup task details / confirmation
-
list_middleware_instance_nodes- List all nodes of a middleware instance.
- Inputs:
middleware_instance_name(string): Middleware Instance Name
- Returns: Array of node objects
-
remove_middleware_instance_nodes- Remove nodes from a middleware instance.
- Inputs:
name(string): Name of the middleware instancenode_names(array[string]): Node Names to remove
- Returns: Operation result / updated node list
-
create_single_redis_middleware- Create a single Redis instance.
- Inputs:
host_name(string): Host Name (required)max_memory_in_gb(integer, default 4): Max Memory In GBname(string | null, default null): Instance Name (optional)
- Returns: Newly created middleware-instance object
-
create_redis_cluster_middleware- Create a Redis Cluster middleware instance.
- Inputs:
name(string | null, default null): Cluster Name (optional)max_memory_in_gb(integer, default 4): Max Memory In GB per nodemaster_host_names(array[string]): Master Host Names (required)replica_host_names(array[string]): Replica Host Names (required)
- Returns: Newly created cluster-instance object
-
add_redis_nodes- Add nodes to a Redis middleware instance.
- Inputs:
name(string): Name of the Redis instance (required)master_host_names(array[string] | null, default null): New Master Hosts (optional)replica_host_names(array[string] | null, default null): New Replica Hosts (optional)
- Returns: Operation result / updated cluster topology
Setup
Obtain an Auth Token
Log in to the MegaCloud console, open your browser’s Network tab while loading any API call, and extract the Authorization: Bearer <token> header value.
Install
Clone the repo:
git clone https://github.com/megaease/megacloud-mcp.git
Then run
pip install "mcp[cli]"
Remember to install mcp command globally for all users.
VS Code Integration
Cline
Install the Cline for VS Code extension.
Set MegaCloud MCP server with following config:
{
"mcpServers": {
"megacloud-mcp": {
"type": "stdio",
"command": "mcp",
"args": [
"run",
"<your-repo-dir>/megacloud-mcp/megacloud_mcp/__main__.py"
],
"env": {
"MEGACLOUD_AUTHTOKEN": "<your-auth-token>"
}
}
}
}
GitHub Copilot
{
"mcp": {
"servers": {
"test-megacloud-mcp": {
"type": "stdio",
"command": "mcp",
"args": [
"run",
"<your-repo-dir>/megacloud-mcp/megacloud_mcp/__main__.py"
],
"env": {
"MEGACLOUD_AUTHTOKEN": "<your-auth-token>"
}
}
}
}
}
Run with Docker
Build the image:
docker build -t megaease/megacloud-mcp .
Settings:
{
"megacloud-mcp": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"MEGACLOUD_AUTHTOKEN",
"megaease/megacloud-mcp"
],
"env": {
"MEGACLOUD_AUTHTOKEN": "<your-auth-token>"
}
}
}
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。