Skip to main content

Datadog MCP Server

Create a powerful Model Context Protocol (MCP) server for Datadog in minutes with our AI Gateway. This guide walks you through setting up seamless Datadog integration with enterprise-grade security and instant API key authentication.

About Datadog API​

Datadog is the essential monitoring and observability platform for cloud-scale applications, providing comprehensive visibility across your entire technology stack. The Datadog API enables programmatic access to:

  • Infrastructure Monitoring: Metrics from servers, containers, and cloud services
  • Application Performance Monitoring (APM): End-to-end request tracing
  • Log Management: Centralized log aggregation and analysis
  • Real User Monitoring (RUM): Frontend performance tracking
  • Security Monitoring: Threat detection and compliance
  • Synthetic Monitoring: Proactive testing and alerting
  • Network Performance Monitoring: Traffic flow analysis
  • Incident Management: Alert orchestration and response

Key Features​

  • REST API v2: Modern API with enhanced capabilities
  • Multi-Region Support: US1, EU1, US3, US5, AP1, FedRAMP
  • Rate Limiting: 300-1000 requests/hour depending on endpoint
  • Real-time Metrics: Sub-minute metric resolution
  • Log Streaming: Real-time log ingestion
  • Custom Metrics: Business-specific KPIs
  • Service Map: Automatic dependency discovery
  • Anomaly Detection: AI-powered insights

What You Can Do with Datadog MCP Server​

The MCP server transforms Datadog's API into a natural language interface, enabling AI agents to:

Metrics & Monitoring​

  • Metric Operations

    • "Show CPU usage for production servers in the last hour"
    • "Alert when memory exceeds 80% on any database server"
    • "Track custom business metrics like checkout conversion rate"
    • "Compare performance metrics between releases"

  • Dashboard Management

    • "Create a dashboard for API performance metrics"
    • "Clone the production dashboard for staging environment"
    • "Update SLO dashboard with new service endpoints"
    • "Generate executive dashboard with key business metrics"

  • Anomaly Detection

    • "Find anomalies in request latency over the past week"
    • "Detect unusual spikes in error rates"
    • "Identify outliers in database query times"
    • "Alert on abnormal user behavior patterns"

Log Management​

  • Log Analysis

    • "Search for all 500 errors in the payment service"
    • "Find logs containing user ID 12345 from yesterday"
    • "Show authentication failures in the last 24 hours"
    • "Correlate error logs with deployment events"

  • Log Patterns

    • "Identify common error patterns in application logs"
    • "Group similar log messages automatically"
    • "Extract fields from unstructured log data"
    • "Create parsing rules for custom log formats"

  • Log Archives

    • "Archive logs older than 30 days to S3"
    • "Rehydrate logs from last month for investigation"
    • "Set retention policies by log source"
    • "Calculate log storage costs by service"

Alerting & Incidents​

  • Alert Configuration

    • "Create alert when API response time exceeds 500ms"
    • "Set up composite alerts for multi-condition scenarios"
    • "Configure anomaly-based alerts for traffic patterns"
    • "Build SLA alerts for critical services"

  • Incident Management

    • "Create incident for current production outage"
    • "Assign incident to on-call engineer"
    • "Update incident status and add timeline events"
    • "Generate post-mortem report with metrics"

  • Alert Routing

    • "Route database alerts to DBA team"
    • "Escalate P1 alerts to management after 15 minutes"
    • "Suppress alerts during maintenance windows"
    • "Configure alert fatigue reduction rules"

APM & Tracing​

  • Service Performance

    • "Show slowest endpoints in the user service"
    • "Trace requests through microservice architecture"
    • "Identify bottlenecks in database queries"
    • "Compare latency across different regions"

  • Error Tracking

    • "Find most frequent errors by service"
    • "Track error rates after deployments"
    • "Identify error patterns by user segment"
    • "Correlate errors with infrastructure issues"

  • Dependency Mapping

    • "Show all services dependent on the auth service"
    • "Identify critical path for checkout flow"
    • "Map database connections by service"
    • "Visualize API call patterns"

Security Monitoring​

  • Threat Detection

    • "Show all security signals from the last hour"
    • "Detect brute force login attempts"
    • "Monitor for suspicious API usage patterns"
    • "Track compliance violations"

  • Security Posture

    • "Audit cloud resource configurations"
    • "Find publicly exposed S3 buckets"
    • "Check for unencrypted databases"
    • "Monitor IAM permission changes"

  • Compliance Reporting

    • "Generate PCI compliance report"
    • "Track GDPR data access requests"
    • "Monitor SOC2 control effectiveness"
    • "Audit security group changes"

Automation & Integration​

  • Workflow Automation

    • "Auto-scale services based on metrics"
    • "Trigger remediation scripts on alerts"
    • "Update CMDB with discovered services"
    • "Sync monitors with infrastructure changes"

  • Synthetic Monitoring

    • "Create API tests for critical endpoints"
    • "Monitor multi-step user journeys"
    • "Test from multiple global locations"
    • "Alert on availability drops"

  • Service Level Objectives

    • "Define SLO for 99.9% uptime"
    • "Track error budget consumption"
    • "Alert when burning through error budget"
    • "Generate SLO compliance reports"

Prerequisites​

  • Access to Cequence AI Gateway
  • Datadog account with appropriate permissions
  • API Key and Application Key from Datadog
  • Understanding of your Datadog region (US1, EU1, etc.)

Step 1: Generate Datadog API Credentials​

Before setting up the MCP server, you need to create API credentials in Datadog.

1.1 Access Datadog Organization Settings​

  1. Log in to your Datadog account
  2. Navigate to Organization Settings (bottom left menu)
  3. Select API Keys under Access section

1.2 Create API Key​

  1. Click New Key
  2. Provide a descriptive name:
    • Example: "AI Gateway MCP Integration"
  3. Copy the generated API key (you'll need this later)
  4. Store it securely - you cannot view it again

1.3 Create Application Key​

  1. Go to Application Keys tab
  2. Click New Key
  3. Provide a descriptive name:
    • Example: "AI Gateway MCP App Key"
  4. Copy the generated application key
  5. Store it securely

1.4 Note Your Datadog Region​

Your Datadog region determines the API endpoint:

  • US1: api.datadoghq.com (default)
  • EU1: api.datadoghq.eu
  • US3: api.us3.datadoghq.com
  • US5: api.us5.datadoghq.com
  • AP1: api.ap1.datadoghq.com
  • US1-FED: api.ddog-gov.com (FedRAMP)

Step 2: Access AI Gateway Apps​

  1. Log in to your Cequence AI Gateway dashboard
  2. Navigate to Apps in the left sidebar
  3. You'll see the list of available third-party applications

Step 3: Find and Select Datadog API​

  1. In the Apps section, browse through the Third-party category
  2. Look for Datadog or use the search function
  3. Click on the Datadog API card to view details

The Datadog API card shows:

  • Number of available endpoints
  • Integration capabilities
  • Quick description of functionality

Step 4: Create MCP Server​

  1. Click the Create MCP Server button on the Datadog API card
  2. You'll be redirected to the MCP Server creation wizard

Step 5: Configure API Endpoints​

In the App Configuration step:

  1. Base URL: Select your Datadog region endpoint
    • Default: https://api.datadoghq.com
    • Or choose your specific region
  2. Select API endpoints to expose to your MCP server based on your needs
  3. Click Next to proceed

Step 6: MCP Server Basic Setup​

Configure your MCP server details:

  1. MCP Server Name: Enter a descriptive name

    • Example: "Datadog Observability Platform"
    • This name will identify your server in the dashboard

  2. Description (Optional): Add details about the server's purpose

    • Example: "Comprehensive monitoring and observability for production infrastructure"

  3. Production Mode: Toggle based on your needs

    • ON for production environments
    • OFF for development/testing

  4. Click Next to continue

Step 7: Configure Authentication​

This is where you'll use your Datadog API credentials:

  1. Authentication Type: Select API Key

  2. Fill in the authentication details:

    • API Key: Paste your Datadog API key
    • Application Key: Paste your Datadog Application key

  3. Additional Headers:

    • The system will automatically configure:
      • DD-API-KEY: {your-api-key}
      • DD-APPLICATION-KEY: {your-application-key}

  4. Click Next to continue

Available Datadog API Capabilities​

The Datadog MCP server provides access to comprehensive monitoring capabilities:

Metrics API​

  • Query Metrics

    • Retrieve time series data
    • Aggregate metrics across tags
    • Calculate rollups and transformations
    • Access custom metrics

  • Submit Metrics

    • Send custom metrics
    • Batch metric submission
    • Update metric metadata
    • Configure metric units

Logs API​

  • Search Logs

    • Query log events
    • Aggregate log data
    • Access log archives
    • Configure log pipelines

  • Log Management

    • Create parsing rules
    • Manage indexes
    • Configure retention
    • Set up archives

Monitors API​

  • Monitor Operations

    • Create and update monitors
    • Manage alert conditions
    • Configure notifications
    • Schedule downtimes

  • Monitor Groups

    • Group related monitors
    • Bulk operations
    • Template management
    • Tag-based organization

Dashboards API​

  • Dashboard Management

    • Create custom dashboards
    • Clone and modify templates
    • Share dashboards
    • Schedule reports

  • Widget Configuration

    • Time series graphs
    • Query value displays
    • Heat maps and distributions
    • Service maps

Events API​

  • Event Tracking
    • Submit custom events
    • Query event stream
    • Correlate with metrics
    • Tag and filter events

Service Management​

  • APM Services

    • Service dependencies
    • Performance metrics
    • Error tracking
    • SLO management

  • Synthetic Tests

    • API tests
    • Browser tests
    • Multi-step journeys
    • Global locations

Step 8: Configure Security​

Set up API protection features:

  1. API Protection: Toggle ON to enable

    • Protects against bot attacks, DDoS, and threats
    • Monitors for suspicious activity
    • Rate limiting and anomaly detection

  2. Protection Features (when enabled):

    • Auto-scaling protection
    • Managed infrastructure
    • Built-in monitoring
    • Zero maintenance required

  3. Click Next to continue

Step 9: Choose Deployment Method​

Select your deployment preference:

  • Fully managed deployment
  • Automatic scaling and monitoring
  • Built-in high availability
  • Features included:
    • Auto-scaling
    • Managed infrastructure
    • Built-in monitoring
    • Zero maintenance

Option B: Deploy with Helm Chart​

  • Self-managed Kubernetes deployment
  • Full control over infrastructure
  • Requires:
    • Kubernetes cluster
    • Helm 3.x installed
    • Container registry access

Click Next after selecting your deployment method.

Step 10: Review and Deploy​

Review your MCP server configuration:

  • MCP Server Name: Your chosen name
  • Base URL: Your Datadog region endpoint
  • Selected Endpoints: Number of endpoints selected
  • Authentication: API Key (Configured)
  • API Protection: Enabled/Disabled
  • Deployment: Cequence Cloud or Helm

Click Create & Deploy to finalize the setup.

Step 11: Post-Deployment Setup​

After successful deployment:

  1. Note the MCP Server URL provided

  2. Test the connection:

    • Click "Test Connection"
    • Should return successful authentication
    • Verify access to selected endpoints

  3. Configure AI Agents:

    • The MCP server is now available for AI agent connections
    • Use the provided server URL in your AI agent configuration

Using Your Datadog MCP Server​

With Claude Desktop​

  1. Open Claude Desktop settings

  2. Add your MCP server:

    {
      "servers": {
        "datadog": {
          "url": "your-mcp-server-url",
          "auth": {
            "type": "api_key",
            "api_key": "your-encrypted-key"
          }
        }
      }
    }

  3. Start using natural language commands:

    • "Show me CPU usage for web servers in the last hour"
    • "Create an alert for high memory usage on database servers"
    • "Find all error logs from the payment service today"
    • "Generate a dashboard for API performance metrics"
    • "What services are experiencing high latency right now?"

API Integration Example​

// Initialize MCP client
const mcpClient = new MCPClient({
  serverUrl: 'your-mcp-server-url',
  auth: {
    type: 'api_key',
    headers: {
      'DD-API-KEY': process.env.DD_API_KEY,
      'DD-APPLICATION-KEY': process.env.DD_APP_KEY
    }
  }
});

// Query metrics
const cpuMetrics = await mcpClient.datadog.metrics.query({
  query: 'avg:system.cpu.user{service:web-app}',
  from: Date.now() - 3600000, // 1 hour ago
  to: Date.now()
});

// Search logs
const errorLogs = await mcpClient.datadog.logs.search({
  query: 'service:payment-api status:error',
  time: {
    from: '1 hour ago',
    to: 'now'
  },
  limit: 100
});

// Create monitor
const monitor = await mcpClient.datadog.monitors.create({
  type: 'metric alert',
  query: 'avg(last_5m):avg:system.memory.used{*} by {host} > 0.9',
  name: 'High Memory Usage Alert',
  message: 'Memory usage is above 90% on {{host.name}}',
  tags: ['team:infrastructure', 'severity:high'],
  options: {
    thresholds: {
      critical: 0.9,
      warning: 0.8
    },
    notify_no_data: true,
    notify_audit: false
  }
});

// Update dashboard
await mcpClient.datadog.dashboards.update({
  id: 'dashboard-id',
  title: 'Application Performance Dashboard',
  widgets: [{
    definition: {
      type: 'timeseries',
      requests: [{
        q: 'avg:trace.servlet.request.duration{*}',
        display_type: 'line'
      }],
      title: 'API Response Time'
    }
  }]
});

Common Use Cases​

Infrastructure Monitoring​

  • Server health tracking
  • Container orchestration metrics
  • Cloud resource utilization
  • Network performance analysis
  • Cost optimization insights

Application Performance​

  • API latency monitoring
  • Error rate tracking
  • Database query optimization
  • Service dependency mapping
  • User journey analysis

Log Intelligence​

  • Centralized log analysis
  • Error pattern detection
  • Security event correlation
  • Compliance auditing
  • Troubleshooting workflows

Incident Response​

  • Automated alert creation
  • On-call rotation management
  • Incident timeline tracking
  • Post-mortem generation
  • SLA compliance reporting

Security Best Practices​

  1. API Key Security:

    • Store keys in secure vault
    • Rotate keys regularly
    • Use separate keys per environment
    • Monitor key usage

  2. Access Control:

    • Limit API key permissions
    • Use role-based access
    • Audit API activity
    • Implement IP allowlists

  3. Rate Limiting:

    • Monitor API usage
    • Implement caching strategies
    • Use batch operations
    • Handle rate limit errors

  4. Data Privacy:

    • Mask sensitive data in logs
    • Implement data retention policies
    • Use log archives for compliance
    • Encrypt data in transit

Troubleshooting​

Common Issues​

  1. 403 Forbidden

    • Verify API key is active
    • Check application key permissions
    • Ensure correct region endpoint
    • Validate IP allowlist settings

  2. 429 Rate Limited

    • Check rate limit headers
    • Implement exponential backoff
    • Use more efficient queries
    • Consider caching responses

  3. 400 Bad Request

    • Validate query syntax
    • Check time range format
    • Verify tag formatting
    • Review API documentation

  4. No Data Returned

    • Verify metric/log exists
    • Check time range
    • Validate tag filters
    • Ensure data retention period

Getting Help​