KosmoKrator

monitoring

Datadog MCP Integration for OpenAI Agents SDK

Connect Datadog to OpenAI Agents SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

10 functions 6 read 4 write API key auth
Submit Datadog feedback View package source

Connect Datadog to OpenAI Agents SDK

Attach KosmoKrator integration tools to OpenAI Agents SDK workflows through a local MCP gateway.

Start the KosmoKrator MCP gateway locally and point the OpenAI Agents SDK MCP tool at that process or wrapper. The gateway is local, scoped to this integration, and starts with --write=deny so OpenAI Agents can inspect read-capable tools without receiving write access by default.

Datadog MCP Config for OpenAI Agents SDK

Use headless JSON commands for CI-style execution and MCP for agent tool discovery.

{
  "mcpServers": {
    "kosmokrator-datadog": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=datadog",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=datadog --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Datadog instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Datadog Tools Visible to OpenAI Agents

OpenAI Agents sees stable MCP tool names generated from the Datadog integration catalog.

MCP toolSource functionTypeDescription
integration__datadog__datadog_list_monitors datadog.datadog_list_monitors Read List Datadog monitors. Optionally filter by name or tags. Returns monitor IDs, names, types, states, and query definitions.
integration__datadog__datadog_get_monitor datadog.datadog_get_monitor Read Get full details of a specific Datadog monitor by ID. Returns the monitor query, thresholds, message, and current state.
integration__datadog__datadog_create_monitor datadog.datadog_create_monitor Write Create a new Datadog monitor. Specify the monitor type, query, name, and optional message and thresholds. Common types: "metric alert", "service check", "event alert".
integration__datadog__datadog_update_monitor datadog.datadog_update_monitor Write Update an existing Datadog monitor. Provide the monitor ID and the fields to update (name, query, message, options, tags, etc.).
integration__datadog__datadog_delete_monitor datadog.datadog_delete_monitor Write Delete a Datadog monitor by ID. This action is permanent and cannot be undone.
integration__datadog__datadog_query_metrics datadog.datadog_query_metrics Read Query Datadog metrics between two timestamps. Use Datadog query syntax (e.g., "avg:system.cpu.user{env:production} by {host}"). Returns time series data points.
integration__datadog__datadog_list_dashboards datadog.datadog_list_dashboards Read List all Datadog dashboards. Returns dashboard IDs, titles, descriptions, and modification dates.
integration__datadog__datadog_get_dashboard datadog.datadog_get_dashboard Read Get full details of a specific Datadog dashboard by ID. Returns the dashboard layout, widgets, and template variables.
integration__datadog__datadog_post_event datadog.datadog_post_event Write Post an event to the Datadog event stream. Specify title, text, priority, tags, and alert type. Events appear in the event timeline.
integration__datadog__datadog_get_current_user datadog.datadog_get_current_user Read Get the currently authenticated Datadog user. Useful for verifying credentials and identifying the connected account.

Related Datadog Pages

Datadog CLIUse direct JSON commands instead of MCP discovery. Datadog MCPFull gateway reference and MCP tool names. KosmoKrator for OpenAI AgentsClient-level gateway setup.