Datadog, verified

MCP server by Datadog · Verified

Query Datadog logs, metrics, traces, monitors, dashboards and incidents from your AI assistant.

OAuth sign-in (You sign in with the vendor the first time you connect)Streamable HTTP

Connect to Datadog

Datadog needs sign-in. Connect with its own URL:

https://mcp.datadoghq.com/api/unstable/mcp-server/mcp

Your client opens Datadog’s sign-in the first time you use it. The token stays between your client and Datadog.

Share this server

Opens this page, with the URL and setup steps.

mcp.tc/i/datadog

About

Connects an AI assistant to a Datadog account so it can read observability data such as logs, metrics, traces, monitors, dashboards and incidents. It is meant for investigating production problems with live data.

It runs as a hosted streamable HTTP endpoint. The URL differs per Datadog site (the US1 endpoint is mcp.datadoghq.com). Users sign in with OAuth, or send DD_API_KEY and DD_APPLICATION_KEY headers as an alternative. The path contains "unstable", so behavior may change.

What you can do

  • Search and read logs
  • Query metrics and traces
  • Inspect monitors and their status
  • Browse dashboards
  • Look up incidents

Tools

Datadog lists its tools only after you sign in, so we can’t show them here. Your client lists them once you’re connected.

Example prompts

  • Show error logs for the checkout service in the last hour

  • Which Datadog monitors are alerting right now?

  • List open incidents and summarize the most recent one

  • Query CPU usage metrics for my production hosts over the last day

Set up

Every client connects to mcp.datadoghq.com, and Datadog asks you to sign in the first time. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http datadog https://mcp.datadoghq.com/api/unstable/mcp-server/mcp
  1. Start Claude Code, type /mcp, pick datadog and choose Authenticate. A browser window opens for the Datadog sign-in.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Settings → Connectors and click Add custom connector.
  2. Name it Datadog and paste this URL:
https://mcp.datadoghq.com/api/unstable/mcp-server/mcp
  1. Click Add, then Connect, and sign in when Datadog asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://mcp.datadoghq.com/api/unstable/mcp-server/mcp and click Add.
  2. Click Connect and sign in when Datadog asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, open Settings → Security and login and turn on Developer mode.
  2. Go to chatgpt.com/plugins and click + to create an app for a remote MCP server.
  3. Paste https://mcp.datadoghq.com/api/unstable/mcp-server/mcp as the server URL and choose OAuth. ChatGPT sends you to Datadog to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "datadog": {
      "url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
    }
  }
}

Cursor shows Needs login next to the server. Click it to sign in.

VS Code

Or from a terminal:

code --add-mcp '{"name":"datadog","type":"http","url":"https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "datadog": {
      "type": "http",
      "url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
    }
  }
}

VS Code asks you to sign in the first time the server starts.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "datadog": {
      "serverUrl": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add datadog --url https://mcp.datadoghq.com/api/unstable/mcp-server/mcp
codex mcp login datadog

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.datadog]
url = "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"

Gemini CLI

gemini mcp add --transport http datadog https://mcp.datadoghq.com/api/unstable/mcp-server/mcp

Then, inside Gemini CLI, run /mcp auth datadog to sign in.

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.

{
  "mcpServers": {
    "datadog": {
      "type": "http",
      "url": "https://mcp.datadoghq.com/api/unstable/mcp-server/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://mcp.datadoghq.com/api/unstable/mcp-server/mcp.

FAQ

Can I paste mcp.tc/i/datadog into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://mcp.datadoghq.com/api/unstable/mcp-server/mcp, so your client talks to Datadog directly. The sign-in token only works there anyway. The quick link is for sharing: it opens this page, with setup steps for every client.

Does Datadog need an API key or a sign-in?

Yes, you need a Datadog account. The first time your client connects, it opens Datadog’s sign-in page. The token goes straight to the server’s own URL, never through mcp.tc.

Is Datadog a remote or a local server?

Remote. Datadog hosts it at https://mcp.datadoghq.com/api/unstable/mcp-server/mcp, and it speaks Streamable HTTP. There’s nothing to install.

What can Datadog do?

You can search and read logs, query metrics and traces and inspect monitors and their status.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT in developer mode, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Who wrote this page?

mcp.tc’s robot read Datadog’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

Embed

Show Datadog in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work

README badge

Badge preview, lightBadge preview, dark
Markdown
[![Datadog on mcp.tc](https://mcp.tc/i/datadog/badge.svg)](https://mcp.tc/i/datadog)
HTML
<a href="https://mcp.tc/i/datadog"><img src="https://mcp.tc/i/datadog/badge.svg" alt="Datadog on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/datadog.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/datadog" title="Datadog on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/datadog.json

What each field means

mcp.tc isn’t affiliated with Datadog. This page was built from Datadog’s public metadata, last checked on 3 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.