
MCP Kubernetes
Enables advanced management of Kubernetes clusters through natural language interactions. Supports querying, managing, and monitoring pods, deployments, nodes, and logs across multiple contexts and namespaces.
README
MCP Kubernetes
Model Context Protocol server for Kubernetes operations.
Description
This project implements an MCP (Model Context Protocol) server for advanced management of Kubernetes clusters. It provides tools to query, manage, and monitor resources such as pods, deployments, nodes, and logs, with support for multiple contexts and namespaces.
Features
- 🟢 Pod Management:
- 📦 List pods by namespace and context.
- 🔍 Retrieve complete pod details, including events, containers, volumes, and status.
- 🚀 Deployment Management:
- 📦 List deployments by namespace and context.
- 📈 Scale replicas and rollout (restart) deployments.
- 📝 Query detailed deployment status.
- 🖥️ Node Management:
- 🗂️ List nodes with capacity, status, roles, and cluster summary.
- 📄 Pod Logs:
- 📝 Retrieve logs from specific pods and containers, with options for previous logs and line count.
- 🔄 Multi-context Support:
- 🔎 Query and switch Kubernetes contexts.
- ⚙️ Set default context.
- ⚙️ Configuration and Logging:
- 🛠️ Utilities for loading Kubernetes configuration and structured logging.
Installation
pip install -r requirements.txt
Usage
Run the MCP server:
python src/mcp_kubernetes/main.py
API Examples
The tools are exposed as MCP functions and can be invoked from compatible clients:
- Get pods:
get_pods(context="my-context", namespace="default")
- Pod details:
get_pod_details(environment="prod", pod_name="nginx-123", namespace="default", context="my-context")
- Get deployments:
get_deployments(context="my-context", namespace="default")
- Scale deployment:
scale_deployment(namespace="default", deployment_name="web", replicas=5)
- Rollout deployment:
rollout_deployment(namespace="default", deployment_name="web")
- Get nodes:
get_nodes(context="my-context")
- Get logs:
get_logs(context="my-context", environment="prod", pod_name="nginx-123", namespace="default", container="nginx")
- Available contexts:
get_available_contexts()
- Change context:
set_default_context(context="other-context")
Project Structure
src/mcp_kubernetes/main.py
: Main entry point for the MCP server.src/mcp_kubernetes/config.py
: Configuration and logging utilities.src/mcp_kubernetes/tools/
: Kubernetes tools modules:deployments.py
: Deployment management.pods.py
: Pod management and details.nodes.py
: Node information and summary.logs.py
: Pod log retrieval.
Contributing
Contributions are welcome! Please open an issue or pull request for suggestions and improvements.
License
MIT License. See the LICENSE file
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。