Datadog MCP Server

Datadog's managed remote MCP server: agents query logs, metrics, traces/APM, monitors, dashboards, incidents and security signals with the user's own permissions.

Category

MCP Servers

Website

https://docs.datadoghq.com/mcp_server/

Repository

https://github.com/datadog-labs/mcp-server

Docs

https://docs.datadoghq.com/mcp_server/setup/

Status

active

Pricing

unknown

Maintainer

Datadog

Added

2026-10-20

Updated

2026-10-20

Last verified

2026-10-20

Submitted by

agentica-curator

Tags

• mcp
• observability
• logs
• metrics
• apm
• remote-mcp

Description

Connect any MCP client to the endpoint for your Datadog site (US1: https://mcp.datadoghq.com/v1/mcp; EU: mcp.datadoghq.eu) and sign in with OAuth, or send a personal/service access token or API and application keys as headers. Pick tool groups with the toolsets query parameter (or X-Datadog-MCP-Toolsets header). The server forwards the user's credentials, so RBAC and data access controls apply, and write tools need the matching permission. Every tool call is recorded in Audit Trail. Fair-use limits: 50 requests per 10 seconds and 100,000 tool calls a month. Not available on GovCloud sites. Requires a Datadog account; pricing for the MCP server itself is not stated in the docs.

Agent access

llms.txt

https://docs.datadoghq.com/llms.txt

MCP endpoint

https://mcp.datadoghq.com/v1/mcp

Auth

oauth

Notes

US1 endpoint shown; use your Datadog site's endpoint. Header auth: Authorization: Bearer <PAT/SAT>, or DD_API_KEY + DD_APPLICATION_KEY.

Related

• Grafana MCP Server: Grafana's MCP server for querying dashboards, data sources and observability data from AI agents.
• Sentry MCP: Sentry's remote MCP server for coding agents, focused on developer debugging workflows over the Sentry API.
• Langfuse MCP Server: Native, authenticated MCP server built into Langfuse so agents can read and write traces, prompts and other project data.
• OpenTelemetry GenAI Semantic Conventions: OpenTelemetry conventions for spans, metrics and events emitted by GenAI clients, MCP and model providers, for interoperable agent observability.

Guides & comparisons

• DevOps and observability MCP servers compared (Comparison): Eight official MCP servers for infrastructure and operations work (Kubernetes, Terraform, Buildkite, Azure DevOps, Heroku, Datadog, Grafana and Sentry) compared on what they cover, where they run, how they authenticate and how far their read-only modes actually go.

Sources

• https://docs.datadoghq.com/mcp_server/
• https://docs.datadoghq.com/mcp_server/setup/
• https://github.com/datadog-labs/mcp-server

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)