OceanBase Kubernetes Control Tool (okctl) MCP Server
LocalAbout OceanBase Kubernetes Control Tool (okctl) MCP Server
The okctl MCP server exposes OceanBase Kubernetes Control Tool operations to clients. It is intended for administrators managing OceanBase clusters, tenants, backup policies, components, and SQL through okctl.
Key features
- 01Create, inspect, scale, update, and upgrade clusters
- 02Manage tenant lifecycle and configuration
- 03Create and control backup policies
- 04Configure connections and execute SQL
- 05Install, update, and list components
- 06Select tool groups and transport options
Use cases
- 01Operate OceanBase clusters in Kubernetes
- 02Manage tenant resources and primary-standby transitions
- 03Configure backups and run cluster SQL
- 04Enable only selected operation groups
MCP support
It exposes okctl-backed tools for OceanBase cluster, tenant, backup policy, component, and SQL operations to MCP clients. Tool groups can be selected, and it supports stdio or SSE transport.
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 READMEOceanBase Kubernetes Control Tool (okctl) MCP Server
English | 简体中文
Project Overview
This project is the MCP server implementation for the OceanBase Kubernetes Control Tool (okctl). It provides a set of tool functions for managing OceanBase clusters, tenants, and backup policies. These functions are implemented by calling the underlying okctl command-line tool and exposing these features to clients through the MCP protocol.
Functional Modules
This project includes the following main tools:
1. Cluster Management (clusters.py)
Provides functionality for creating, deleting, viewing, scaling, updating, and upgrading OceanBase clusters.
list_all_clusters()- List all OceanBase clustersshow_cluster()- Display detailed information of a specified clustercreate_cluster()- Create a new OceanBase clusterdelete_cluster()- Delete a specified OceanBase clusterscale_cluster()- Scale an OceanBase clusterupdate_cluster()- Update OceanBase cluster configurationupgrade_cluster()- Upgrade OceanBase cluster version
2. Tenant Management (tenants.py)
Provides functionality for creating, deleting, viewing, scaling, updating, and managing OceanBase tenants.
list_tenants()- List all tenantscreate_tenant()- Create a new tenantdelete_tenant()- Delete a specified tenantshow_tenant()- Display tenant detailed informationscale_tenant()- Scale tenant resourcesupdate_tenant()- Update tenant configurationupgrade_tenant()- Upgrade tenant versionchange_tenant_password()- Change tenant passwordactivate_tenant()- Activate standby tenantreplay_tenant_log()- Replay tenant logsswitchover_tenant()- Switch between primary and standby tenants
3. Backup Policy Management (backup_policy.py)
Provides functionality for creating, deleting, viewing, updating, and managing OceanBase backup policies.
list_backup_policies()- List all backup policiescreate_backup_policy()- Create a new backup policydelete_backup_policy()- Delete a specified backup policyshow_backup_policy()- Display backup policy detailed informationupdate_backup_policy()- Update backup policypause_backup_policy()- Pause backup policyresume_backup_policy()- Resume backup policy
4. SQL Operations (sql.py)
Provides functionality for configuring database connections and executing SQL queries on OceanBase clusters.
configure_cluster_connection()- Configure database connection to a cluster- Parameters: cluster_name, tenant_name (default: "sys"), namespace (default: "default"), user, password (if not provided, will use environment variable OB_CLUSTER_PASSWORD), port (default: 2881)
- Returns: Database connection configuration information
execute_cluster_sql()- Execute SQL queries on a cluster- Parameters: query, cluster_name (optional), tenant_name (default: "sys"), database (default: "oceanbase"), namespace (default: "default")
- Returns: Query results
- Supports various SQL commands including SELECT, SHOW TABLES, SHOW COLUMNS, DESCRIBE, and DML statements
5. Component Management (components.py)
Provides functionality for installing, updating, and managing OceanBase components.
list_components()- List all installed componentsinstall_component()- Install a new componentupdate_component()- Update component
Development Environment Setup
Prerequisites
- Python 3.10 or higher installed
- uv package manager installed (uv official documentation)
- OceanBase Kubernetes Control Tool (okctl) installed and configured
- Kubernetes environment configured with access permissions to OceanBase clusters
Configuring the MCP Server
{
"mcpServers": {
"okctl-mcp-server-py": {
"command": "uv",
"args": ["--directory", "/path/to/okctl-mcp-server", "run", "src/okctl/server.py"],
"env": {
// you need to set these environment variables if you want to connect to cluster by root@sys
"OB_CLUSTER_PASSWORD": "<password of cluster>"
}
}
}
}
Command Line Arguments
-
--tools: Specify which tools to enable, comma separated. Options:all: Enable all tools (default)clusters: Enable cluster management tools onlytenants: Enable tenant management tools onlybackup_policy: Enable backup policy management tools onlycomponents: Enable component management tools onlysql: Enable SQL operation tools only
Example:
--tools=clusters,tenants,sql -
--use_sse: Use Server-Sent Events (SSE) transport instead of stdio -
--port: Specify the port for SSE transport (default: 8000)
Important Notes
- The server needs to run in an environment with access to the Kubernetes cluster
- All functions are implemented by calling the underlying okctl command-line tool, so ensure okctl is properly installed and configured
- Most functions provide a namespace parameter with a default value of "default", which can be specified as needed
- Some operations (such as deleting clusters, deleting tenants) may be irreversible, please proceed with caution
- When executing SQL queries, it is recommended to provide a more precise prompt, otherwise it may return an error
- It is recommended to perform backups before executing important operations
Contributing
Issues and Pull Requests are welcome to improve this project.
License
This project is licensed under the Apache 2.0 License.
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.