Datadog (US1) MCP connector
The Datadog (US1) connector brings monitors, incidents, logs, traces, metrics and dashboards from Datadog's US1 region into Claude, ChatGPT, Cursor and the Elaichi Agent, so your team can ask about production in plain language.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Datadog (US1) to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Datadog (US1) once
-
Open Connections, choose Add connection, and pick Datadog (US1).
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Datadog (US1). Datadog (US1)'s own window opens. Whoever approves it decides what this connection can reach.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Datadog (US1) MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Datadog (US1) MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Datadog (US1) MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Datadog (US1) to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Datadog (US1) through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
SRE
Pull the picture together during an incident
Ask what fired, which hosts are affected and what the error logs say while the incident in Datadog (US1) is still open. Get the answer in one place instead of six tabs.
-
Engineering
Trace a slow request to its cause
Find the spans behind a slow endpoint, compare them with the metric for that service and see where the time goes.
-
Support
Check whether a customer's problem is real
When a customer reports errors, look up the RUM events and logs for their session in Datadog (US1) before replying, so the answer is grounded in what actually happened.
-
Platform
Review monitors before they go live
Validate a new monitor against Datadog (US1), compare it with the monitor templates your team already uses and check which monitor group it belongs in.
-
Engineering leadership
Write the postmortem from the real timeline
Search events and incidents for the window in question, then create a notebook in Datadog (US1) with the timeline and the metrics that mattered, ready for the review.
-
Security
Look for unusual activity in logs
Analyze logs across hosts in Datadog (US1) for failed logins, unexpected geographies or spikes from a single source, and search the dashboards your team already built for the same signal.
Try asking
- “Which monitors are alerting right now and on which hosts?”
- “Summarize the error logs for the checkout service in the last hour.”
- “Draft a notebook with the timeline of incident 4821.”
Compare
Elaichi vs Zapier MCP vs Composio for Datadog (US1)
All three can connect Datadog (US1) to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Datadog (US1) tools | Allow or restrict single Datadog (US1) tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Datadog (US1) call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
AI tools
Datadog (US1) tools for your AI agents
352 tools are ready to call through Elaichi's MCP endpoint the moment you connect Datadog (US1), governed by the same roles, restrictions, and audit log as everything else in Elaichi. Datadog (US1) builds and runs these tools.
No tools match your search.
Showing 313 of 352 Datadog (US1) tools here. Connect Datadog (US1) and call search_tools or tools/list over the MCP endpoint for the complete set.
See it in Elaichi
What connecting Datadog (US1) gets you
6 screens from the product, each doing one job for your Datadog (US1) account.
The agent
Ask about production in plain language.
Which monitors are alerting, what the logs say, answered from live Datadog (US1) records.
- monitors
- incidents
- logs
- dashboards
Ask Elaichi to work across your apps.
Which monitors are alerting right now and on which hosts?
Summarize the error logs for the checkout service in the last hour.
Draft a notebook with the timeline of incident 4821.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One governed endpoint for Claude, ChatGPT and Cursor.
Datadog (US1) from any MCP client over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
352 Datadog (US1) tools, no code to write.
Monitors, incidents, logs, traces, metrics, dashboards and notebooks, all cataloged and ready to call.
- Search Datadog (US1) events
- Get Datadog (US1) incident
- Get Datadog (US1) metric
- Get Datadog (US1) metric context
Toolboxes
Every team gets its own toolbox.
Scope SRE to incidents and Support to logs, each toolbox built for one team's work.
- SRE
- Engineering
- Support
- Platform
Shared connections
Teammates work through a connection, never a credential.
See who connected each Datadog (US1) account and which teams and members share it.
- Production
- Staging
- Platform
- Support
Audit log
Every call answers who did what.
When, who, what happened, type and resource, for every search of Datadog (US1) logs.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule starts the work, a person approves.
Incidents are fetched, grouped, drafted into a digest, then posted to Datadog (US1) after approval.
Datadog (US1) digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch monitors
Datadog (US1)
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Datadog (US1)
Queued
Collections and dashboards
Incident health, computed, with no model involved.
Four metrics, 14 days of incidents created and a team breakdown, refreshed on a schedule.
Datadog (US1) health
Refreshed 4 minutes ago · every 15 minutes · from the monitors collection
Monitors
1,284 ↓ 12%
Incidents
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Monitors created
Last 14 days
By team
Share of activity
Production 34%
Staging 27%
Platform 21%
Support 18%
FAQ
Frequently asked questions
How do I connect Datadog (US1) to Claude?
Connect Datadog (US1) in Elaichi first, then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Datadog's own step is a normal OAuth sign-in: you log in to your Datadog US1 account and approve access. There is no OAuth application to register and no client ID or secret to generate.
Does Datadog (US1) work with ChatGPT and Cursor as well as Claude?
Yes. Once Datadog (US1) is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Datadog in US1 once and every client picks it up.
What can an AI agent actually do with my Datadog (US1) data?
It can search monitors, incidents, events, logs, traces, spans, hosts, metrics, RUM events and dashboards in Datadog (US1), and it can create or edit notebooks and validate a monitor definition before you save it. Ask it which monitors are alerting right now, what the error logs for a service say, or to draft a notebook with an incident's timeline. Short, concrete asks like these work better than long sentences.
Does connecting Datadog (US1) give the AI access to my whole organization?
No. Every call to Datadog in US1 runs as the person who signed in, so the AI sees exactly the dashboards, logs and monitors that person can already see in Datadog, and nothing more. Elaichi can narrow that access further with restrictions, but it can never widen it beyond what Datadog itself grants.
Can I stop an agent from changing things in Datadog (US1)?
Yes. Restrictions in Elaichi apply per action, so you can allow searching monitors, logs and incidents in Datadog (US1) while blocking the creation or editing of notebooks. A restricted action is never advertised to the AI client at all, so no prompt, however worded, can reach it.
What happens to a Datadog (US1) connection when someone leaves?
Offboarding that person in Elaichi ends their access to Datadog in US1 at once, across Claude, ChatGPT, Cursor and every other client. If they had shared a Datadog (US1) connection with a team, it keeps working for everyone else. Disconnecting Datadog (US1) once in Elaichi removes it from every client.
Does the Datadog (US1) MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Datadog (US1) is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Datadog (US1)?
Yes. Both let Claude, ChatGPT or Cursor use Datadog (US1). Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Datadog (US1) call.
How is Elaichi different from Composio for Datadog (US1)?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Datadog (US1): one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Datadog (US1) in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.