OpenTelemetry MCP

為什麼要用

核心特性

Unified MCP for querying OpenTelemetry traces across Jaeger, Tempo, Datadog, and other backends.
Maintained by traceloop (community)
Written in Python
188+ GitHub stars at last check
Open source on GitHub

即時演示

實際使用效果

opentelemetry-mcp-server.replay ▶ 就緒

0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "opentelemetry-mcp-server": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/traceloop/opentelemetry-mcp-server"
      ]
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "opentelemetry-mcp-server": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/traceloop/opentelemetry-mcp-server"
      ]
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "opentelemetry-mcp-server": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/traceloop/opentelemetry-mcp-server"
      ]
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "opentelemetry-mcp-server": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/traceloop/opentelemetry-mcp-server"
      ]
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "opentelemetry-mcp-server",
      "command": "TODO",
      "args": [
        "See README: https://github.com/traceloop/opentelemetry-mcp-server"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "opentelemetry-mcp-server": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/traceloop/opentelemetry-mcp-server"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add opentelemetry-mcp-server -- TODO 'See README: https://github.com/traceloop/opentelemetry-mcp-server'

一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。

使用場景

實戰用法： OpenTelemetry MCP

Use OpenTelemetry MCP for its primary workflow

👤 Developers using AI coding agents ⏱ ~10 min beginner

何時使用： You need the capability: Unified MCP for querying OpenTelemetry traces across Jaeger, Tempo, Datadog, and other backends.

前置條件

MCP server installed — See https://github.com/traceloop/opentelemetry-mcp-server for install instructions

步驟

Install

Install OpenTelemetry MCP following the README at https://github.com/traceloop/opentelemetry-mcp-server✓ 已複製

→ MCP server appears in your client's available tools/skills
Invoke

Use OpenTelemetry MCP to complete the task described in its docs.✓ 已複製

→ Agent calls the relevant tool/skill and returns a result

結果： Working integration with the capabilities advertised by the project.

注意事項

README is the source of truth; details here may lag upstream — Check https://github.com/traceloop/opentelemetry-mcp-server for the latest setup steps and tool list