metoro-mcp-server
Official
metoro-mcp-服务器
此仓库包含 Metoro MCP(模型上下文协议)服务器。此 MCP 服务器允许您通过 Claude 桌面应用与您的 Kubernetes 集群进行交互!
什么是 MCP(模型上下文协议)?
您可以在此处阅读有关模型上下文协议的更多信息: https://modelcontextprotocol.io
但简而言之
模型上下文协议 (MCP) 是一种开放协议,支持 LLM 应用程序与外部数据源和工具之间的无缝集成。无论您是构建 AI 驱动的 IDE、增强聊天界面,还是创建自定义 AI 工作流,MCP 都提供了一种标准化的方式,将 LLM 与其所需的上下文连接起来。
Related MCP server: OpenTelemetry MCP Server
Metoro 是什么?
Metoro是一个专为 Kubernetes 中运行的微服务设计的可观测性平台,它使用基于 eBPF 的检测工具,无需更改代码即可生成深度遥测数据。eBPF 代理生成的数据会被发送到 Metoro 的后端进行存储,并通过我们的 API 发送到 Metoro 的前端。
该 MCP 服务器将这些 API 公开给 LLM,以便您可以向 AI 询问有关 Kubernetes 集群的问题。
演示
https://github.com/user-attachments/assets/b3f21e9a-45b8-4c17-8d8c-cff560d8694f
如何使用 Metoro MCP 服务器?
确保已安装Golang 。对于 mac,
brew install go;对于 ubuntu,sudo apt-get install golang。克隆存储库:
git clone https://github.com/metoro-io/metoro-mcp-server.git导航到存储库目录:
cd metoro-mcp-server构建服务器可执行文件:
go build -o metoro-mcp-server
如果您已经拥有 Metoro 帐户:
在“设置” ->“用户设置”中,从你的 Metoro 帐户复制你的授权令牌。在~/Library/Application Support/Claude/claude_desktop_config.json中创建一个文件,内容如下:
{
"mcpServers": {
"metoro-mcp-server": {
"command": "<your path to Metoro MCP server go executable>/metoro-mcp-server",
"args": [],
"env": {
"METORO_AUTH_TOKEN" : "<your auth token>",
"METORO_API_URL": "https://us-east.metoro.io"
}
}
}
}如果您没有 Metoro 帐户:
不用担心,您仍然可以使用Live Demo Cluster进行尝试。其中包含的令牌是演示令牌,可供任何人公开使用。在~/Library/Application Support/Claude/claude_desktop_config.json中创建一个包含以下内容的文件:
{
"mcpServers": {
"metoro-mcp-server": {
"command": "<your path to Metoro MCP server go executable>/metoro-mcp-server",
"args": [],
"env": {
"METORO_AUTH_TOKEN" : "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjdXN0b21lcklkIjoiOThlZDU1M2QtYzY4ZC00MDRhLWFhZjItNDM2ODllNWJiMGUzIiwiZW1haWwiOiJ0ZXN0QGNocmlzYmF0dGFyYmVlLmNvbSIsImV4cCI6MTgyMTI0NzIzN30.7G6alDpcZh_OThYj293Jce5rjeOBqAhOlANR_Fl5auw",
"METORO_API_URL": "https://demo.us-east.metoro.io"
}
}
}
}完成
claude_desktop_config.json编辑后,保存文件并重新启动 Claude Desktop 应用程序。现在,您应该会在 Claude 桌面应用的 MCP 服务器下拉列表中看到 Metoro MCP 服务器。您已准备好在 Claude 桌面应用上使用 Metoro MCP 服务器了!
内置
该服务器建立在我们的Golang MCP SDK之上。
This server cannot be deployed
Maintenance
Related MCP Connectors
Query application logs, traces, and metrics from your AI coding assistant via Foam's MCP server.
- SuperlogOAuthsh.superlog
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
- SpanlyOAuthcom.spanly
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
Analytics for MCP servers. Query your tool calls, first-call success, retries and schema cost.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables interactive Kubernetes cluster monitoring and troubleshooting through natural language queries. Users can diagnose pod issues, check service status, and investigate cluster problems using conversational AI.-
- FlicenseAqualityDmaintenanceEnables AI agents to query Prometheus metrics and Loki logs for intelligent alert investigation and troubleshooting. Provides service discovery, metric querying, log searching, and correlation tools to help identify root causes of issues.9-
- AlicenseAqualityCmaintenanceConnects AI assistants to Warpmetrics telemetry data to monitor AI agent performance, execution runs, and LLM costs. It allows users to query success rates, latency, and spend metrics directly through natural language interfaces.2095 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to interact with Monti APM for Meteor application performance monitoring.28 npm5MIT