Multi-Cluster MCP Server
# Open Cluster Management MCP Server
The **OCM MCP Server** provides a robust gateway for Generative AI (GenAI) systems to interact with multiple Kubernetes clusters through the Model Context Protocol (MCP). It facilitates comprehensive operations on Kubernetes resources, streamlined multi-cluster management, and delivered interactive cluster observability.
## **🚀 Features**
### 🛠️ MCP Tools - Kubernetes Cluster Awareness
- ✅ Retrieve resources from the **hub cluster** (current context)
- ✅ Retrieve resources from the **managed clusters**
- ✅ Connect to a **managed cluster** using a specified `ClusterRole`
- ✅ Access resources across multiple Kubernetes clusters(via Open Cluster Management)
- 🔄 Retrieve and analyze **metrics, logs, and alerts** from integrated clusters
- ❌ Interact with multi-cluster APIs, including Managed Clusters, Policies, Add-ons, and more
<details>
<summary>Mutiple Kubernetes Clusters Operations</summary>
[](https://asciinema.org/a/706281)
</details>
### 📦 Prompt Templates for Open Cluster Management *(Planning)*
- Provide reusable prompt templates tailored for OCM tasks, streamlining agent interaction and automation
### 📚 MCP Resources for Open Cluster Management *(Planning)*
- Reference official OCM documentation and related resources to support development and integration
### **📌 How to Use**
Configure the server using the following snippet:
```json
{
"mcpServers": {
"multicluster-mcp-server": {
"command": "npx",
"args": [
"-y",
"multicluster-mcp-server@latest"
]
}
}
}
```
**Note:** Ensure `kubectl` is installed. By default, the tool uses the **`KUBECONFIG`** environment variable to access the cluster. In a multi-cluster setup, it treats the configured cluster as the **hub cluster**, accessing others through it.
## License
This project is licensed under the [MIT License](LICENSE).
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: clusters lists clusters, connect_cluster generates access credentials, kube_executor runs kubectl commands, and prometheus queries metrics. The descriptions clearly differentiate their functions, eliminating any ambiguity for an agent.
The naming is mixed with no consistent pattern: clusters is a noun, connect_cluster uses verb_noun, kube_executor uses a compound noun, and prometheus is a proper noun. While readable, the lack of a uniform convention (e.g., all verb_noun or all nouns) reduces predictability.
With 4 tools, the count is slightly low but reasonable for a multi-cluster Kubernetes management server. It covers core operations like listing clusters, accessing them, executing commands, and monitoring metrics, though it could benefit from additional tools for more comprehensive management.
The toolset covers key areas (discovery, access, execution, monitoring) but has notable gaps for a multi-cluster domain, such as creating/deleting clusters, managing resources across clusters, or handling configurations. Agents can work around this for basic tasks, but advanced operations may be limited.