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。

🛡️ Official✓ VerifiedStreamable HTTPOAuth 2.1🛡️ A+~378 tok6 tools
Streamable HTTPhttps://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"

接入步骤

  1. 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"。
  2. 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。
  3. 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)

ToolSafetyDescriptionParameters
query_metrics
~80 tok
🟢 ReadQuery metric timeseries with a Datadog query string.query*: stringfrom: stringto: string
search_logs
~64 tok
🟢 ReadSearch logs with a Datadog log query.query*: stringtimeRange: string
list_monitors
~65 tok
🟢 ReadList monitors with optional state filter.query: stringstate: string
get_monitor
~54 tok
🟢 ReadGet a monitor's definition and current state.monitorId*: string
list_dashboards
~49 tok
🟢 ReadList dashboards matching a query.query: string
list_incidents
~46 tok
🟢 ReadList declared incidents.state: string

更多连接指南