Agents pull metrics and logs around an incident to speed diagnosis.
Observability
Datadog MCP server
Give AI agents governed access to the Datadog MCP server through one audited gateway. Scoped permissions, full observability, and tamper-evident logs on every tool call.
What is the Datadog MCP server?
The Datadog MCP server is an open Model Context Protocol (MCP) server that connects AI agents to Datadog metrics, logs, monitors, and incidents. Through it an agent can query telemetry, search logs, and inspect monitors without bespoke integration code, while the Averta MCP Gateway keeps every action scoped and audited.
Query time-series metrics over a window.
Search logs with facets and filters.
List monitors and their alert states.
Read a monitor's configuration and status.
List dashboards and their widgets.
Read events from the event stream.
List active and resolved incidents.
Search APM traces by service and resource.
Read host health and tags.
Mute or unmute a monitor.
Why the Averta MCP Gateway
Centralized governance
Unified authentication, audit logging, and rate control for every Datadog MCP connection.
Observability and control
Real-time visibility into usage, anomalies, and SLA compliance across every request.
One-click deployment
Enable the Datadog MCP server for your AI teams through one governed gateway, with no manual setup.
Enterprise hardening
High availability, security, and compliance alignment turn MCP from a developer utility into production-grade infrastructure.
OAuth and SSO enforcement
Enterprise authentication and SSO applied automatically to every Datadog endpoint.
Shared and per-user auth
Configure service accounts or per-user access, with secrets protected and centralized revocation.
One managed endpoint
Connect agents to Datadog through a single governed endpoint instead of locally run servers, improving your security posture.
Granular tool access control
Allow only the tools each role needs. Enable read-only access and block write tools like create and delete.
Works with every major AI platform
CognitionBuilt for enterprise teams.
Cloud, private VPC, embedded SDK, or gateway integration. Run Averta where your data, policies, and auditors need it.
Cloud (SaaS)
Fully managed by Averta. Fastest path to production, no infrastructure to run.
Private / VPC
Deploy in your own environment, so data never leaves your boundary.
Embedded SDK & Proxy
Drop Averta into your stack at the SDK or proxy layer, wherever your agents run.
Gateway Integration
Route agent traffic through the gateway, so policy and audit apply at the edge.
Datadog MCP use cases
Where teams put the Datadog MCP server to work, governed end to end through the Averta MCP Gateway.
Why did checkout error rate spike at 2pm?
YouSummarized the spike and likely cause.
- Querying error metrics
- Correlating with logs
All actions logged and governed
Powering safe AI execution at leading teams.
Cyfrin secures its production AI agents with Averta.
Book a demo“Averta gave our agents enforceable boundaries for the dev environment, so instructions like ‘don’t read .env files’ became policy instead of polite suggestions.”
Mikhail Karan
Head of Engineering
Explore other MCP servers
Browse allDatadog MCP server, answered
Security and setup questions teams ask before connecting the Datadog MCP server to AI agents.
Yes. The Averta MCP Gateway sits between your AI agents and any MCP server, giving each agent scoped, per-agent permissions, applying allow, escalate, or block policies on every tool call, and recording a tamper-evident audit of every action. The “Why the Averta MCP Gateway” section on this page covers what it enforces.
It is as safe as the controls around it. The server exposes production telemetry and monitor controls through one token, so scoping and auditing matter. The Averta MCP Gateway keeps reads automatic and monitor changes behind approval, with every call recorded.
Yes. Tool-level policy lets queries and searches run automatically while muting or editing monitors escalates for approval, all recorded.
Route agents through Averta's MCP Gateway for scoped per-agent permissions, tool-level policy, and tamper-evident audit across every Datadog action.
Yes. Datadog provides an official MCP server for its observability data. Routing it through the Averta MCP Gateway keeps each agent read-scoped where it should be, with monitor changes behind approval and every call logged.
Any MCP-compatible client, including Claude and Claude Code, can connect to the Datadog MCP server. Pointing those clients at the Averta MCP Gateway instead of the raw server adds scoped permissions, approval policies, and a tamper-evident log without changing the client setup.
See Averta OS in action
Book a demo and see how Averta OS secures your AI agents from input to execution.
Book a demo