Datadog MCP Server bridges your Datadog observability platform with AI assistants through the Model Context Protocol
Visit WebsiteReviews onG2Capterra
1059 reviews trackedThe Bottom Line
Entry price
Free, no paid tier
Biggest pro
Covers the core Datadog workflow, metrics, logs, monitors, SLOs, and services in one server
Biggest con
Requires Datadog API and application keys, no standalone functionality
TL;DR - Datadog MCP Server
- MCP server connecting Datadog observability data to AI assistants like Claude and Cursor
- Provides 12 tools for querying metrics, logs, monitors, SLOs, services, and CI/CD pipelines
- Open-source npm package requiring Datadog API keys, read-only access to your monitoring stack
Pricing: Free forever
Best for: Individuals & startups
4.5/5 across review platforms
What is Datadog MCP Server?
Datadog MCP Server bridges your Datadog observability platform with AI assistants through the Model Context Protocol. It gives LLMs like Claude structured access to metrics, logs, monitors, SLOs, service definitions, CI/CD pipelines, and team information, enabling natural language queries against your monitoring infrastructure.
The server provides 12 core tools: listing and querying metrics with flexible aggregation and grouping, fetching service logs filtered by environment and time range, managing monitors and SLOs, retrieving service definitions with ownership metadata, listing CI pipelines with fingerprint extraction for Terraform, and viewing teams with member details. Each tool supports multiple output formats and filtering options.
Available as an open-source npm package, the server connects to the Datadog API using your API and application keys. Datadog also offers official MCP Server documentation and LLM Observability features that trace MCP client calls with structured metadata about invoked tools, parameters, and responses. The server works with Claude Desktop, Claude Code, Cursor, and other MCP-compatible clients, making it straightforward to investigate incidents, analyze metrics, or review service health through conversational AI.
Available on: Web
Pros & Cons
Pros
- Covers the core Datadog workflow, metrics, logs, monitors, SLOs, and services in one server
- Flexible querying with aggregation, grouping, and time-range filters for precise results
- Open-source npm package with straightforward API key configuration
- Works with Claude Desktop, Claude Code, Cursor, and other MCP clients
- CI/CD pipeline fingerprints enable infrastructure-as-code workflows
Cons
- Requires Datadog API and application keys, no standalone functionality
- Read-only access, cannot create or modify monitors, dashboards, or alerts
- Community-maintained package, not an official Datadog product
- No dashboard or notebook content retrieval in the open-source version
Ratings Across the Web
4.5(1,059 reviews)
Ratings aggregated from independent review platforms. Learn more
Key Features
Metric querying with custom time ranges, aggregation methods, filters, and groupingService log retrieval filtered by environment, log level, and time rangeMonitor and SLO listing with tag-based and name-based filteringService definition access including metadata, ownership, and configuration detailsCI/CD pipeline listing with fingerprint extraction for Terraform integrationTeam and member information retrieval with multiple output formatsMetric field discovery, list all available tags and values for any metricLLM Observability integration for tracing MCP client tool calls
Pricing Plans
Open Source
Free
- Full source code access
- Community support
- Self-hosted
Reviews
4.5/5
Across 1,059 verified user reviews on G2, Capterra
Add your hands-on experience to help the next buyer.
Best Datadog MCP Server Alternatives
Top alternatives based on features, pricing, and user needs.
DynatracePaid
Full-stack observability and AIOps platform
New RelicFreemium
Full-stack observability with 50+ monitoring capabilities
Grafana CloudFreemium
Unify metrics, logs, traces, and dashboards for complete observability across your stack.
HoneycombFreemium
Observability for distributed systems
LightstepFreemium
Distributed tracing and observability
Still deciding?
Most buyers shortlist 2 or 3 tools before committing. Pull a side-by-side comparison or browse the full alternatives shortlist below.
Explore More
Datadog MCP Server FAQ
Can Datadog MCP Server create or modify monitors and dashboards?
No. The open-source MCP server provides read-only access to metrics, logs, monitors, SLOs, services, and CI/CD pipelines. You can query and analyze data but cannot create alerts, modify dashboards, or change monitor configurations through the server.
Does it work with Datadog EU or other regions?
Yes. You configure the Datadog API endpoint via the
DD_SITE environment variable. Set it to datadoghq.eu for EU, us3.datadoghq.com for US3, us5.datadoghq.com for US5, or ddog-gov.com for government deployments.What permissions do the API keys need?
You need a Datadog API key (for authentication) and an application key (for authorization). The application key inherits the permissions of the user who created it. For full functionality, the user should have read access to metrics, logs, monitors, SLOs, and service catalog.
Is this an official Datadog product?
The npm package (
@anthropic-ai/mcp-server-datadog) is community-maintained, not an official Datadog product. However, Datadog has published official MCP Server documentation and integrates MCP tracing into their LLM Observability product for monitoring MCP client calls.Source: docs.datadoghq.com