mimiops-mcp

mimiops-mcp

Enables AI agents to safely observe and troubleshoot Kubernetes workloads, with limited recovery actions like pod deletion and Helm rollbacks, while preventing dangerous modifications.

Category
访问服务器

README

Mimiops MCP Server

Motivation

There are many ways to manage Kubernetes workloads, but there are also many ways to break them by accident. We have already seen cases where AI agents did something that we did not expect. Giving an AI agent full access to Kubernetes can be risky, especially when it can create, update, or delete resources directly.

In my opinion, we need to provide safe and well-defined tools for AI agents. These tools should limit what an agent can do, validate changes before applying them, and help prevent dangerous operations.

We also need tools that can help investigate and fix workload issues. Many workloads are already managed by well-known tools such as Argo CD, FluxCD, Helm, and other GitOps or deployment systems. An AI agent should understand who manages a resource and avoid making direct changes that can conflict with these tools.

The goal is not to give AI full control of Kubernetes. The goal is to give AI a safe interface that allows it to understand problems, suggest changes, and perform only controlled operations.

Overview

Mimi OPS is not designed to give AI agents unrestricted Kubernetes access. Instead, it provides a small set of well-known and controlled operations.

The agent can observe, investigate, and perform a limited number of safe recovery actions. More dangerous operations, such as editing arbitrary resources, applying YAML, changing secrets, or deleting persistent data are strongly restricted.

This makes Mimi OPS an opinionated interface between AI agents and Kubernetes: powerful enough for common troubleshooting, but limited enough to reduce the risk of unexpected changes.

Kubernetes basic tools:

  • Pods
    • list — list pods and their current status.
    • get — get detailed information about a pod.
    • describe — inspect pod status, conditions, events, and related information.
    • logs — read container logs for troubleshooting.
    • delete — safely restart a workload by deleting a pod and allowing its controller to recreate it.
  • CronJobs and Jobs
    • list — list CronJobs and Jobs.
    • get — get information about a specific resource.
    • describe — inspect status, conditions, events, and failures.
  • Deployments, StatefulSets, and DaemonSets
    • list — list workloads and their current status.
    • get — get information about a specific workload.
    • describe — inspect replicas, rollout status, conditions, and related events.

Helm integration

Mimi OPS can inspect Helm-managed workloads and help recover them when a deployment fails:

  • list — list Helm releases.
  • describe — show release information, status, revision, and related resources.
  • rollback — roll back a release to a previous working revision when the current release is in a broken state.

FluxCD integration

Mimi OPS can work with FluxCD-managed resources without directly changing resources that are controlled by GitOps:

  • Reconcile Flux source resources to fetch the latest configuration.
  • Reconcile HelmRelease resources to retry or apply the expected Helm state.
  • Inspect reconciliation status and errors to understand why a deployment is not ready.

Installation

A Kubernetes MCP (Model Context Protocol) server written in Go. It exposes Kubernetes operations to MCP clients (Claude Desktop, Cursor, VS Code, etc.) over two transports:

  • mimiops-mcp mcp — stdio, for desktop MCP clients.
  • mimiops-mcp server — HTTP/SSE, for web/remote MCP clients.

Running

Common flags

Flags are global (persistent) and accepted on both subcommands:

Flag Default Description
--kubeconfig <path> auto Path to kubeconfig (defaults to $KUBECONFIG then ~/.kube/config)
--context <name> current-context Kubernetes context to use
--namespace <name> all namespaces Scope operations to a namespace
--allow-destructive false Enable destructive tools (e.g. pods_delete)
--log-level <level> info debug, info, warn, error

Per-command flags:

Command Flag Default Description
server --port 8080 HTTP/SSE listen port

Examples

# stdio against a specific context
./bin/mimiops-mcp mcp --kubeconfig ~/.kube/dev.yaml --context prod-east

# SSE server scoped to a namespace, with destructive tools enabled
./bin/mimiops-mcp server --namespace default --allow-destructive --port 8080

Development

make lint       # golangci-lint
make unit       # unit tests (build tag `unit`)
make test       # lint + unit
make licenses   # license audit (forbidden/restricted/unknown)
make docs       # (Docker image docs targets are also available; see `make help`)

Use make help for a full target list.

License

Apache-2.0

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选