MCP Kubernetes Ro
未认领A read-only Kubernetes MCP server: list resources, get resource details, retrieve pod logs, discover API resources, and perform base64 encoding/decoding operations - all while maintaining security through read-only access.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'mcp-kubernetes-ro' -- 'npx' '-y' '@patrickdappollonio/mcp-kubernetes-ro'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Security服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
22 个工具中显示 22 个
文档中列出的工具 (22)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
api_version
(optional): API version for the resource (e.g., 'v1', 'apps/v1')
container
(optional): Container name (required for multi-container pods)
context
(optional): Kubernetes context to use (defaults to current context from kubeconfig)
continue
(optional): Continue token for pagination (from previous response)
data
(required): Text data to encode
field_selector
(optional): Field selector to filter resources (e.g., 'status.phase=Running')
grep_exclude
(optional): Exclude lines matching these patterns (comma-separated). Works like grep -v - excludes lines containing any of these patterns
grep_include
(optional): Include only lines matching these patterns (comma-separated). Works like grep - includes lines containing any of these patterns
id
(required): Port forward session ID (e.g., "pf-1")
label_selector
(optional): Label selector to filter resources (e.g., 'app=nginx,version=1.0')
limit
(optional): Maximum number of resources to return (defaults to all)
max_lines
(optional): Maximum number of lines to retrieve
name
(required): Resource name
namespace
(optional): Target namespace (leave empty for cluster-scoped resources)
node_name
(optional): Specific node name to get metrics for. If not provided, returns metrics for all nodes.
pod
(required): Pod name
pod_name
(optional): Specific pod name to get metrics for. Requires namespace if specified.
ports
(required): Array of port mappings, each with:
previous
(optional): Return logs from the previous terminated container instance (like kubectl logs --previous)
resource_type
(required): The type of resource to list - use plural form (e.g., 'pods', 'deployments', 'services')
since
(optional): Return logs newer than this time. Supports durations like "5m", "1h", "2h30m", "1d" or absolute times like "2023-01-01T10:00:00Z"
use_regex
(optional): Whether to treat grep patterns as regular expressions instead of literal strings