如何将 Datadog Observability 远程 MCP 连接到 OpenAI Codex CLI
约 1 分钟即可把 Datadog 的远程 MCP 服务端接入 OpenAI Codex CLI。如需排查 OAuth / 401 问题,可先用 OAuth 2.1 调试器体检端点。
Streamable HTTPhttps://mcp.datadoghq.com/api/unstable/mcp-server/mcp
Install in Cursor →
Or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"datadog": {
"url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
}
}
}claude mcp add --transport http datadog https://mcp.datadoghq.com/api/unstable/mcp-server/mcp
Install in VS Code →
Or add to .vscode/mcp.json:
{
"servers": {
"datadog": {
"type": "http",
"url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
}
}
}- Open Settings → Connectors (Integrations) → Add Custom Connector.
- Paste the endpoint URL:
https://mcp.datadoghq.com/api/unstable/mcp-server/mcp - Complete the browser OAuth 2.1 login flow when prompted.
Bridge the remote endpoint into stdio with mcp-remote in claude_desktop_config.json:
{
"mcpServers": {
"datadog": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"datadog": {
"serverUrl": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
}
}
}Add to ~/.kiro/settings/mcp.json (or .kiro/settings/mcp.json in your workspace), then reopen Kiro's Agent panel to pick up the server:
{
"mcpServers": {
"datadog": {
"url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
}
}
}Add to ~/.codex/config.toml — Codex reads remote HTTP servers from [mcp_servers.*] tables:
[mcp_servers.datadog] url = "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
Add to cline_mcp_settings.json (Cline → MCP Servers → Configure), or paste it via Cline's MCP marketplace file:
{
"mcpServers": {
"datadog": {
"type": "streamableHttp",
"url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
}
}
}Add to ~/.gemini/settings.json under mcpServers — httpUrl for Streamable HTTP, url for legacy SSE:
{
"mcpServers": {
"datadog": {
"httpUrl": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
}
}
}接入步骤
- 编辑 TOML 配置 — 打开
~/.codex/config.toml,加入[mcp_servers.datadog]与url = "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"。 - 配置凭据 — 首次调用时客户端会打开 Datadog 的 OAuth 授权页面——点击允许后工具即可用。
- 验证 — 在 在线 Inspector 中粘贴
https://mcp.datadoghq.com/api/unstable/mcp-server/mcp并运行 initialize + tools/list 验证连通性。
🧰 工具预览(6)
| Tool | Safety | Description | Parameters |
|---|---|---|---|
| query_metrics ~80 tok | 🟢 Read | Query metric timeseries with a Datadog query string. | query*: stringfrom: stringto: string |
| search_logs ~64 tok | 🟢 Read | Search logs with a Datadog log query. | query*: stringtimeRange: string |
| list_monitors ~65 tok | 🟢 Read | List monitors with optional state filter. | query: stringstate: string |
| get_monitor ~54 tok | 🟢 Read | Get a monitor's definition and current state. | monitorId*: string |
| list_dashboards ~49 tok | 🟢 Read | List dashboards matching a query. | query: string |
| list_incidents ~46 tok | 🟢 Read | List declared incidents. | state: string |
更多连接指南
GitHub MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
Notion MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
Linear MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
Figma Dev Mode MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
AWS Knowledge → OpenAI Codex CLI
连接至 OpenAI Codex CLI →
Stripe MCP → OpenAI Codex CLI
连接至 OpenAI Codex CLI →