Datadog MCP Server
Connect to the Datadog MCP server to query metrics, search logs, manage monitors and incidents, and track SLOs and synthetic tests using AI agents on Gumloop, Claude, or Cursor.
Try Datadog now
Type what you want done. Sign in and run it live with an AI agent.
|
Datadog
Installation
Get StartedCreate a Gumloop Account
To use this MCP, you need a Gumloop account. If you don't have one yet, you can create one for free.
Copy Your Server URL
Copy your MCP server URL and add it to your client. You'll be prompted to authorize on first use.
Tools (44)
List Monitors
List all monitors in your Datadog account with optional filtering by name, tags, or monitor_tags. Returns monitor details including ID, name, type, query, and current state.
Get Monitor
Get detailed information about a specific monitor by ID, including its configuration, state, and history.
Mute Monitor
Mute a monitor to temporarily suppress notifications. Useful during maintenance windows or known issues.
Unmute Monitor
Unmute a previously muted monitor to resume notifications.
Create Monitor
Create a new monitor in Datadog with specified type, query, and alerting configuration.
Update Monitor
Update an existing monitor's configuration including query, thresholds, and notifications.
Delete Monitor
Delete a monitor from Datadog by its ID.
Query Metrics
Query timeseries metrics data from Datadog. Supports aggregation and grouping by tags.
List Metrics
List available metrics in your Datadog account. Use this to discover metric names before querying. By default, returns metrics active in the last 24 hours.
Search Logs
Search and retrieve log events from Datadog. Supports filtering by query, time range, and indexes.
List Incidents
List incidents in your Datadog account with optional filtering by state or query.
Get Incident
Get detailed information about a specific incident including timeline and responders.
What is Datadog MCP?
The Datadog MCP server gives AI agents access to your Datadog observability data. That means agents can query metrics, search logs, create and manage monitors, triage and resolve incidents, build dashboards, track SLOs, schedule maintenance downtimes, and run synthetic tests. It covers the core Datadog surfaces your engineering and SRE teams work in: monitors, metrics, logs, incidents, dashboards, hosts, events, downtimes, SLOs, and synthetics.
If your on-call engineers spend incidents jumping between dashboards, logs, and metrics to figure out what broke, or your platform team edits monitor configs and writes up post-mortems by hand, an AI agent can pull the signals together and handle the busywork. Describe what you need, and your AI agent will handle the Datadog work for you.
MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of writing code against the Datadog API, setting headers, and handling pagination and regions yourself, you add your Datadog API key and Application key to Gumloop once. After that, you query metrics, manage monitors, and triage incidents just by asking your AI agent in plain language.
Related MCP servers
PagerDuty MCP Server
Interact with PagerDuty incident management and on-call scheduling
Incident.io MCP Server
Interact with Incident.io to manage incidents, users, alerts, and incident response workflows
Linear MCP Server
Interact with Linear issue tracking and project management
JIRA MCP Server
Interact with JIRA for project management, issue tracking, and user information access.
Github MCP Server
Server for interacting with Github
Slack MCP Server
Interact with Slack channels and messages
What you can do with Datadog MCP on Gumloop
Monitor and alert on anything
List, create, update, mute, and delete monitors across metric, log, SLO, and composite alert types. An AI agent can stand up a new alert from a description, tune thresholds, or mute noisy monitors during a deploy.
Query metrics and discover signals
Run timeseries metric queries with aggregation and grouping, and list available metric names to find the right signal. An agent can pull CPU, latency, or error-rate trends and reason about anomalies without you ever opening a graph.
Search and analyze logs
Full-text search across log events with time-range filters, index scoping, and pagination for large result sets. Your AI agent can find the relevant log lines during an incident and summarize what they show.
Track and resolve incidents
List, create, update, close, and delete incidents, and pull an incident’s timeline. An agent can open an incident from an alert, keep its status current, and assemble the timeline for a post-mortem.
Build and manage dashboards
List, read, create, update, and delete dashboards with configurable widget layouts. An AI agent can spin up a focused dashboard for a service or incident from a plain-language description.
Monitor infrastructure hosts
List hosts with filters, get active and up host totals, and mute or unmute hosts during maintenance. Useful for fleet visibility and silencing noise while you work.
Schedule maintenance downtimes
Create and cancel scheduled downtimes that automatically silence monitors during a maintenance window, so an agent can quiet alerts before a deploy and clean up afterward.
Track SLOs and run synthetic tests
List, create, update, and delete SLOs and pull historical SLI data, and manage synthetic API and browser tests, including triggering them on demand to validate a deploy or check endpoint health.
How to connect the Gumloop Datadog MCP Server
- 1
Create a free Gumloop account
Sign up at gumloop.com. No credit card required.
- 2
Add the Datadog MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Datadog in your AI workflows
That's it. Your AI agent can now query metrics, search logs, manage monitors and incidents, and track SLOs across your Datadog account. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Datadog MCP use cases
AI-assisted incident response for on-call and SRE
When an incident opens, a Gumloop agent can pull the related monitor states, query the relevant metrics, search recent logs, and check host health, then post a clear summary to Slack. On-call engineers start triage with context instead of a blank dashboard.
Automated post-mortems for SRE teams
Pull an incident’s full details and timeline along with SLO history for the affected service, then have an AI agent draft a structured post-mortem with impact, timeline, and contributing factors into a doc. The team reviews a draft instead of starting from scratch.
Monitor and SLO management as code for platform teams
From a spec in a sheet or repo, an AI agent can create and update monitors and SLOs in bulk, keep thresholds consistent across services, and mute the right monitors during a planned change. Observability config stays consistent without manual clicking.
Deploy and maintenance automation for DevOps
Before a release, an agent can schedule a downtime or mute the affected hosts, then trigger synthetic tests after the deploy and alert the team in Slack if any checks fail. Maintenance windows run themselves and nobody forgets to re-enable alerts.
Reliability reporting for engineering leadership
On a schedule, an agent can query key metrics, pull SLO status and host totals, list open incidents, and compile a weekly reliability report into Google Sheets or a Slack message. Leaders get a current view of system health without anyone assembling it by hand.
Why use Gumloop for Datadog MCP
Add your Datadog keys once, stored securely, no env vars or code
Most Datadog MCP servers you’ll find on GitHub make you store your API key and Application key in environment variables and write code to set headers, pick the right region, and handle pagination. With Gumloop, you add your API key and Application key once and they’re stored securely, with no need for config files, token juggling, or coding against the Datadog API.
Works with multiple MCP clients
Use the Datadog MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop agents. Same server URL, works with any MCP client.
Chain Datadog with 100+ other integrations
Combine Datadog with Slack, PagerDuty, Jira, Linear, and other MCP tools in a single AI agent. An agent can detect an incident in Datadog, open a ticket in Jira, and post a summary to Slack, all in one run.
Enterprise-grade and scalable
Built for teams, with role-based permissions and dedicated support for Pro users. For details on Gumloop’s security practices, see trust.gumloop.com.
Pricing includes a free plan
You can test the Datadog MCP integration on Gumloop’s free tier before committing. Paid plans start at $37/month.
Frequently asked questions
Ship Datadog agents in minutes
Connect any AI agent to 100+ MCP servers, zero setup.