Datadog Connector for AI agents.
11 live capabilities
Query performance metrics and search logs across your cloud infrastructure.
Waiting for input…
Why people use Datadog
Datadog Infrastructure Monitoring and Log Analysis
This Connector changes that by bringing the data to you. You can stay in your chat or editor and ask your agent to pull specific metrics or find error traces. You get the answers you need without ever leaving your workspace.
What Vinkius changes
You get a conversational interface for your entire Datadog observability stack.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Finding the root cause of a spike
A developer notices a latency spike.
- Real-world use case 02
Checking maintenance status
An SRE sees an alert but wants to know if it's planned.
- Real-world use case 03
Managing alert fatigue
A DevOps engineer wants to silence a flapping monitor.
Complete set · 11capabilities
The complete Datadog capability set.
These are the exact actions your AI can choose when you ask it to work with Datadog.
01—04
4 capabilities in this set.
Part of 11 available through Datadog.
- 01 Capability
Query metrics
Pull time-series data for specific infrastructure or app metrics. Use it to see how CPU or memory usage changes over time.
- 02 Capability
Mute monitor
Silence a specific monitor for a set period. This is perfect for ignoring known issues during maintenance.
- 03 Capability
List downtimes
See planned maintenance windows and their current status. This helps you avoid chasing ghost issues during scheduled work.
- 04 Capability
List slos
View your Service Level Objectives and their current compliance. Use it to see if your app is meeting its uptime targets.
05—08
4 capabilities in this set.
Part of 11 available through Datadog.
- 05 Capability
Search logs
Find specific log entries that match your query. It's great for spotting errors or specific status codes across your apps.
- 06 Capability
List monitors
See all your monitors and their current states like alert or ok. This gives you a quick overview of your system health.
- 07 Capability
Get monitor
Get the full details of a specific monitor, including its thresholds. Use it to understand exactly why a monitor is firing.
- 08 Capability
List events
Pull a list of events like alerts and deployment logs. Use it to see what happened in your environment recently.
09—11
3 capabilities in this set.
Part of 11 available through Datadog.
- 09 Capability
List dashboards
Get a list of all your dashboard IDs and titles. This helps you find the right visualization quickly.
- 10 Capability
Get dashboard
See the full configuration and widgets for a specific dashboard. This helps you understand how a dashboard is built.
- 11 Capability
List hosts
Get a list of your infrastructure hosts and their tags. Use it to see which cloud resources are currently active.
Set up in minutes
One URL. Then ask Datadog to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Datadog from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_v7in3QWy0ApCG2tAnOZzEFbhEmNkQfEznkXebVEX/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Datadog, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Datadog for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_v7in3QWy0ApCG2tAnOZzEFbhEmNkQfEznkXebVEX/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Datadog URL.
- Step 03
Save and start
Save the connection and enable Datadog in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"datadog": {
"url": "https://edge.vinkius.com/vk_preview_v7in3QWy0ApCG2tAnOZzEFbhEmNkQfEznkXebVEX/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Datadog
Open Agent mode in chat and ask: "Using Datadog, help me...". 11 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"datadog": {
"url": "https://edge.vinkius.com/vk_preview_v7in3QWy0ApCG2tAnOZzEFbhEmNkQfEznkXebVEX/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Datadog
Ask Copilot: "Using Datadog, help me...". 11 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"datadog": {
"url": "https://edge.vinkius.com/vk_preview_v7in3QWy0ApCG2tAnOZzEFbhEmNkQfEznkXebVEX/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Datadog
Open Cascade and ask: "Using Datadog, help me...". 11 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"datadog": {
"url": "https://edge.vinkius.com/vk_preview_v7in3QWy0ApCG2tAnOZzEFbhEmNkQfEznkXebVEX/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Datadog
Ask Cline: "Using Datadog, help me...". 11 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add datadog --transport http "https://edge.vinkius.com/vk_preview_v7in3QWy0ApCG2tAnOZzEFbhEmNkQfEznkXebVEX/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Datadog
Ask Claude: "Using Datadog, show me...". 11 tools are ready
Where the request belongs
Work Datadog can move forward.
The DevOps engineer who's tired of clicking through dozens of dashboards at 2am to find a single spike. The developer who needs to see logs without switching windows.
DevOps Engineer
Audits alerts and checks system health during active incidents without leaving the chat.
Software Developer
Searches application logs for 500 errors while debugging features in the IDE.
SRE
Monitors active alerts and tracks performance trends during high-pressure response windows.
System Admin
Verifies monitor configurations and host attributes through natural language queries.
When one Connector is not enough
Carry the request into a workflow.
Combine Datadog with the systems that finish the task.
View all recipesGet Instant Incident Alerts in Discord via MCP
Monitors fire, Discord gets the alert, the incident log updates itself , no human in the loop
MCP Recipe for Full-Stack Observability
Two monitoring capabilities, zero correlation , your Datadog alerts say 'high latency' and your Grafana dashboards say 'database connections maxed' but nobody connected the dots until the postmortem
MCP Recipe for Pre-Mortem System Analysis
Architecture red-teamed, failure modes quantified, monitoring alerts created , pre-mortem your system before production breaks it
Connectors for Cache Performance Monitoring
Your Redis cache has 47,000 keys but only 3,200 are ever accessed , the rest are ghosts from features you deleted 6 months ago, silently eating memory and money
Connectors for Monitored Deploy Orchestration
PR merged, deployment triggered, health check passed , and the deploy summary posted itself to the PR thread
Connectors to Find Your Most Expensive APIs
API traffic metered, cache savings calculated, origin load measured, cost projections generated , optimize your API infrastructure costs with data
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsDatadog
Monitor infrastructure, applications, and logs with unified observability that gives you full-stack visibility in real time.
AppDynamics (Application Performance Monitor API)
Monitor application performance, business transactions, and infrastructure health rules directly from your AI agent.
New Relic
Monitor and query your entire stack via New Relic NerdGraph. track entities, NRQL, and alerts directly from your AI agent.
Prometheus
Monitor your infrastructure with Prometheus. run PromQL queries, analyze metrics, and manage time-series data directly from your AI agent.
Dynatrace (APM and Observability)
Monitor and manage your Dynatrace environment. query metrics, track problems, manage entities, and automate observability workflows directly from your AI agent.
SigNoz (Datadog Alternative)
Monitor infrastructure and manage alert rules via SigNoz. list, create, and update observability alerts directly from your AI agent.
Bring your own AI
Change the model, client or framework. Keep Datadog connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Datadog.
The practical details behind the request, access and result.
Can I use the Datadog MCP to see my server health?
Yes, you can check your system health by asking the agent to list monitors or query specific metrics. It gives you a real-time look at what's running and what's failing.
How do I connect my Datadog account to my AI agent?
You'll need your Datadog API Key, APP Key, and Site. Once you provide those to your AI client, the agent can start querying your infrastructure.
Can it help me find specific errors in my logs?
Yes, it can search logs using specific queries. You can ask for logs containing specific error codes, status levels, or structured attributes.
Can I silence alerts using this Connector?
Yes, you can use the mute_monitor capability to silence specific monitors for set periods. This is great for ignoring known issues during maintenance.
Does this Connector work for cloud infrastructure?
Yes, it works with any host or service you have in Datadog, including cloud provider attributes and agent versions.
Can I see my SLO status?
Yes, you can ask the agent to list your Service Level Objectives. It will return your target percentages, time windows, and current compliance status.
Can my agent query specific Datadog metrics using DDQL?
Yes. Use the 'query_metrics' capability. Provide your DDQL query string and the target time range. The agent will fetch the numeric timeseries data directly from Datadog's telemetry datastores.
How do I search for a specific error message across my application logs?
Use the 'search_logs' capability. Provide a query matching your error string and an ISO time boundary. The agent will retrieve the structural extraction of logs matching those parameters to help you identify failures.
Can I see which monitors are currently in an alert state?
Absolutely. The 'list_monitors' capability allows you to filter by group state (e.g., 'alert,warn'). The agent pulls the explicitly configured system triggers to show you which services are currently unhealthy.
One connection away
Give your agent a direct line to Datadog.
Connect Datadog once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available