NewCost control: a token allowance a month for each model choice — when one runs out, the cheaper one answers.See how it works
memtro
MCP server · Engineering and operations

Datadog MCP server

Datadog in any MCP client, through Memtro: Datadog does not publish this server. Memtro's Datadog connector reads Datadog through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Read-only Datadog: monitors and their alert state, log search and facet counts, metric time series, events, incidents and SLO status.

Reads

  • datadog_monitorsDatadog monitors: list/search them (filter by state alert|warn|"no data"|ok, tags like env:prod…
  • datadog_logsSearch Datadog logs with log search syntax (service:web status:error "timeout", @http.status_code:>=500, host:ip-1, -status:info) in a time window…
  • datadog_metricsQuery a Datadog metric time series with a metrics query string, e.g. "avg:system.cpu.user{env:prod} by {host}"…
  • datadog_eventsSearch the Datadog event stream (monitor alerts and recoveries, deployments, custom events) with event search syntax…
  • datadog_incidents_slosDatadog Incident Management and SLOs.

Connect it

First connect Datadog on Dashboard → Connections, then add Memtro to your client once. The Datadog tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

One command registers the server; the tools are then available in every session.

claude mcp add --transport http memtro https://platform.memtro.com/api/mcp \
  --header "Authorization: Bearer sk-memtro-..."

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Datadog connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

  • › What is alerting in Datadog right now?
  • › Show error logs for the checkout service in the last 30 minutes
  • › How many 5xx responses per service in the last hour?
  • › Plot p99 latency for the api service over the last 6 hours
  • › Which incidents were resolved this week and how long did they take?
  • › Is the payments SLO within its error budget?

Questions

Is this an official Datadog MCP server?
No. It is Memtro's MCP server with Memtro's Datadog connector behind it: the connector reads Datadog through its API with the credentials you connect on Dashboard → Connections, and Datadog publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?
Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in Datadog?
Not yet. Today every Datadog tool reads, searches or lists; when it gains actions, each is marked, granted by name and used only when you ask, so nothing is created, sent, updated or deleted until you say so.
Which clients work?
Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Engineering and operations