如何将 PagerDuty Incident 远程 MCP 连接到 OpenAI Codex CLI

约 1 分钟即可把 PagerDuty 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+~371 tok6 tools
Streamable HTTPhttps://mcp.pagerduty.com/mcp

Add to ~/.codex/config.toml — Codex reads remote HTTP servers from [mcp_servers.*] tables:

[mcp_servers.pagerduty]
url = "https://mcp.pagerduty.com/mcp"

接入步骤

  1. 编辑 TOML 配置 — 打开 ~/.codex/config.toml,加入 [mcp_servers.pagerduty] 与 url = "https://mcp.pagerduty.com/mcp"。
  2. 配置凭据 — 首次调用时客户端会打开 PagerDuty 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.pagerduty.com/mcp 并运行 initialize + tools/list 验证连通性。

🧰 工具预览(6)

ToolSafetyDescriptionParameters
list_incidents
~71 tok
🟢 ReadList incidents filtered by status and service.status: stringserviceId: string
get_incident
~57 tok
🟢 ReadGet incident details including alerts and log entries.incidentId*: string
acknowledge_incident
~51 tok
🟠 WriteAcknowledge an incident.incidentId*: string
resolve_incident
~68 tok
🟠 WriteResolve an incident with a note.incidentId*: stringresolution: string
list_services
~45 tok
🟢 ReadList PagerDuty services.query: string
get_oncall
~59 tok
🟢 ReadGet who is currently on call for a schedule or escalation policy.scheduleId*: string

更多连接指南