Dynatrace MCP Server
Dynatrace ships an officially supported REMOTE Model Context Protocol server named `dynatrace-mcp`, hosted inside each customer's own Dynatrace SaaS environment and reached over Streamable HTTP at a per-tenant URL. It fronts Grail (DQL), Davis AI analyzers, Davis Copilot, problems, Kubernetes events, security findings, Smartscape entities and documents as MCP tools. A separate community-supported LOCAL stdio server (`@dynatrace-oss/dynatrace-mcp-server`) was deprecated at version 2.1.2 on 2026-07-20 and Dynatrace now directs local-development users to the Dynatrace-for-AI skills repo plus the `dtctl` CLI, and agent-to-agent/remote users to the hosted server.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
Grail Query Agent— Generates a DQL query from a natural-language prompt. Does not execute the query.DQL Explanation Agent— Provides a natural-language explanation of a DQL query.Help Agent— Answers general Dynatrace product questions via Davis Copilot conversations.Data Analysis Agent— Executes any valid DQL query and returns the raw result. Grail responses are capped at 1000 records.Root Cause Agent— Returns an overview list of all problems in the environment, filterable to active or closed.Root Cause Details Agent— Returns the details of one specific Davis problem.Kubernetes Agent— Returns events for Kubernetes clusters, all clusters or specific ones.Forecasting Agent— Predicts future timeseries values with a statistical forecasting model.Changepoint Agent— Analyzes timeseries data to find events, outliers and significant trends.Document Agent— Finds user-accessible Dashboards and Notebooks by name.Troubleshooting Agent— Finds globally shared troubleshooting-guide Dashboards and Notebooks from a problem description. Requires "Enable document suggestion" in Settings.Smartscape Agent— Resolves an entity name from its ID and an ID from its name.Static Threshold Analysis Agent— Detects anomalies using fixed thresholds that a metric should not violate.Seasonal Baseline Agent— Detects anomalies against a learned seasonal baseline.Auto-adaptive Threshold Analysis Agent— Detects anomalies by learning a single threshold from the data distribution that separates outliers from normal observations.Security Posture Agent— Returns compliance findings and misconfigurations from the last Dynatrace Security Posture Management run.Runtime Vulnerability Agent— Returns all open (muted and non-muted) vulnerabilities from the last Runtime Vulnerability Analytics report.Security Event Details Agent— Returns the latest security event or scan event details for a finding ID, scan ID or title.Security Summary Agent— Runs a DQL query returning an overview of ingested external security events and Dynatrace detection findings.Log Pattern Agent— Finds common patterns across log lines by running a DQL query and analyzing individual lines.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.