Dynatrace MCP Server
The local Dynatrace MCP server allows AI Assistants to interact with the Dynatrace observability platform, bringing real-time observability data directly into your development workflow.
Note: This product is not officially supported by Dynatrace.
If you need help, please contact us via GitHub Issues if you have feature requests, questions, or need help.
https://github.com/user-attachments/assets/25c05db1-8e09-4a7f-add2-ed486ffd4b5a
Quickstart
You can add this MCP server to your MCP Client like VSCode, Claude, Cursor, Amazon Q, Windsurf, ChatGPT, or Github Copilot via the command is npx -y @dynatrace-oss/dynatrace-mcp-server (type: stdio). For more details, please refer to the configuration section below.
Furthermore, you need to configure the URL to a Dynatrace environment:
DT_ENVIRONMENT(string, e.g.,https://abc12345.apps.dynatrace.com) - URL to your Dynatrace Platform (do not use Dynatrace classic URLs likeabc12345.live.dynatrace.com)
Once you are done, we recommend looking into example prompts, like Get all details of the entity 'my-service' or Show me error logs. Please mind that these prompts lead to executing DQL statements which may incur costs in accordance to your licence.
Architecture
Use cases
- Real-time observability - Fetch production-level data for early detection and proactive monitoring
- Contextual debugging - Fix issues with full context from monitored exceptions, logs, and anomalies
- Security insights - Get detailed vulnerability analysis and security problem tracking
- Natural language queries - Use AI-powered DQL generation and explanation
- Multi-phase incident investigation - Systematic 4-phase approach with automated impact assessment
- Advanced transaction analysis - Precise root cause identification with file/line-level accuracy
- Cross-data source correlation - Connect problems → spans → logs with trace ID correlation
- DevOps automation - Deployment health gates with automated promotion/rollback logic
- Security compliance monitoring - Multi-cloud compliance assessment with evidence-based investigation
Capabilities
- List and get problem details from your services (for example Kubernetes)
- List and get security problems / vulnerability details
- Execute DQL (Dynatrace Query Language) and retrieve logs, events, spans and metrics
- Send Slack messages (via Slack Connector)
- Set up notification Workflow (via Dynatrace AutomationEngine)
- Get more information about a monitored entity
- Get Ownership of an entity
- Create, list, and read documents (Notebooks, Dashboards, Launchpads, and other Dynatrace documents)
Costs
Important: While this local MCP server is provided for free, using certain capabilities to access data in Dynatrace Grail may incur additional costs based
on your Dynatrace consumption model. This affects execute_dql tool and other capabilities that query Dynatrace Grail storage, and costs
depend on the volume (GB scanned).
Before using this MCP server extensively, please:
- Review your current Dynatrace consumption model and pricing
- Understand the cost implications of the specific data you plan to query (logs, events, metrics) - see Dynatrace Pricing and Rate Card
- Start with smaller timeframes (e.g., 12h-24h) and make use of buckets to reduce the cost impact
- Set an appropriate
DT_GRAIL_QUERY_BUDGET_GBenvironment variable (default: 1000 GB) to control and monitor your Grail query consumption
Grail Budget Tracking:
The MCP server includes built-in budget tracking for Grail queries to help you monitor and control costs:
- Set
DT_GRAIL_QUERY_BUDGET_GB(default: 1000 GB) to define your session budget limit - The server tracks bytes scanned across all Grail queries in the current session
- You'll receive warnings when approaching 80% of your budget
- Budget exceeded alerts help prevent unexpected high consumption
- Budget resets when you restart the MCP server session
To understand costs that occured:
Execute the following DQL statement in a notebook to see how much bytes have been queried from Grail (Logs, Events, etc...):
fetch dt.system.events
| filter event.kind == "QUERY_EXECUTION_EVENT" and contains(client.client_context, "dynatrace-mcp")
| sort timestamp desc
| fields timestamp, query_id, query_string, scanned_bytes, table, bucket, user.id, user.email, client.client_context
| maketimeSeries sum(scanned_bytes), by: { user.email, user.id, table }
AI-Powered Assistance (Preview)
- Natural Language to DQL - Convert plain English queries to Dynatrace Query Language
- DQL Explanation - Get plain English explanations of complex DQL queries
- AI Chat Assistant - Get contextual help and guidance for Dynatrace questions
- Feedback System - Provide feedback to improve AI responses over time
Note: While Davis CoPilot AI is generally available (GA), the Davis CoPilot APIs are currently in preview. For more information, visit the Davis CoPilot Preview Community.
Configuration
You can add this MCP server (using STDIO) to your MCP Client like VS Code, Claude, Cursor, Amazon Q Developer CLI, Windsurf Github Copilot via the package @dynatrace-oss/dynatrace-mcp-server.
We recommend to always set it up for your current workspace instead of using it globally.
VS Code
{
"servers": {
"npx-dynatrace-mcp-server": {
"command": "npx",
"cwd": "${workspaceFolder}",
"args": ["-y", "@dynatrace-oss/dynatrace-mcp-server@latest"],
"envFile": "${workspaceFolder}/.env"
}
}
}
Please note: In this config, the ${workspaceFolder} variable is used.
This only works if the config is stored in the current workspaces, e.g., <your-repo>/.vscode/mcp.json. Alternatively, this can also be stored in user-settings, and you can define env as follows:
{
"servers": {
"npx-dynatrace-mcp-server": {
"command": "npx",
"args": ["-y", "@dynatrace-oss/dynatrace-mcp-server@latest"],
"env": {
"DT_ENVIRONMENT": ""
}
}
}
}
Claude Desktop
{
"mcpServers": {
"dynatrace-mcp-server": {
"command": "npx",
"args": ["-y", "@dynatrace-oss/dynatrace-mcp-server@latest"],
"env": {
"DT_ENVIRONMENT": ""
}
}
}
}
Amazon Q Developer CLI
The Amazon Q Developer CLI provides an interactive chat experience directly in your terminal. You can ask questions, get help with AWS services, troubleshoot issues, and generate code snippets without leaving your command line environment.
{
"mcpServers": {
"dynatrace-mcp-server": {
"command": "npx",
"args": ["-y", "@dynatrace-oss/dynatrace-mcp-server@latest"],
"env": {
"DT_ENVIRONMENT": ""
}
}
}
}
This configuration should be stored in <your-repo>/.amazonq/mcp.json.
Amazon Kiro
The Amazon Kiro is an agentic IDE that helps you do your best work with features such as specs, steering, and hooks.
{
"mcpServers": {
"dynatrace-mcp-server": {
"command": "npx",
"args": ["-y", "@dynatrace-oss/dynatrace-mcp-server@latest"],
"env": {
"DT_ENVIRONMENT": ""
}
}
}
}
This configuration should be stored in <your-repo>/.kiro/settings/mcp.json.
Google Gemini CLI
The Google Gemini CLI is Google's official command-line AI assistant that supports MCP server integration. You can add the Dynatrace MCP server using either the built-in management commands or manual configuration.
Using gemini CLI directly (recommended):
gemini extensions install https://github.com/dynatrace-oss/dynatrace-mcp
export DT_PLATFORM_TOKEN=... # optional
export DT_ENVIRONMENT=https://...
and verify that the server is running via
gemini mcp list
Or manually in your ~/.gemini/settings.json or .gemini/settings.json:
{
"mcpServers": {
"dynatrace": {
"command": "npx",
"args": ["@dynatrace-oss/dynatrace-mcp-server@latest"],
"env": {
"DT_ENVIRONMENT": ""
},
"timeout": 30000,
"trust": false
}
}
}
HTTP Server Mode (Alternative)
For scenarios where you need to run the MCP server as an HTTP service instead of using stdio (e.g., for stateful sessions, load balancing, or integration with web clients), you can use the HTTP server mode:
Running as HTTP server:
# Get help and see all available options
npx -y @dynatrace-oss/dynatrace-mcp-server@latest --help
# Run with HTTP server on default port 3000
npx -y @dynatrace-oss/dynatrace-mcp-server@latest --http
# Run with custom port (using short or long flag)
npx -y @dynatrace-oss/dynatrace-mcp-server@latest --server -p 8080
npx -y @dynatrace-oss/dynatrace-mcp-server@latest --http --port 3001
# Run with custom host/IP (using short or long flag)
npx -y @dynatrace-oss/dynatrace-mcp-server@latest --http --host 127.0.0.1 # recommended for local computers
npx -y @dynatrace-oss/dynatrace-mcp-server@latest --http --host 0.0.0.0 # recommended for container
npx -y @dynatrace-oss/dynatrace-mcp-server@latest --http -H 192.168.0.1 # recommended when sharing connection over a local network
# Check version
npx -y @dynatrace-oss/dynatrace-mcp-server@latest --version
Configuration for MCP clients that support HTTP transport:
{
"mcpServers": {
"dynatrace-http": {
"url": "http://localhost:3000",
"transport": "http"
}
}
}
Rule File
For efficient result retrieval from Dynatrace, please consider creating a rule file (e.g., .github/copilot-instructions.md, .amazonq/rules/), instructing coding agents on how to get more details for your component/app/service. Here is an example for easytrade, please adapt the names and filters to fit your use-cases and components:
# Observability
We use Dynatrace as an Observability solution. This document provides instructions on how to get data for easytrade from Dynatrace using DQL.
## How to get any data for my App
Depending on the query and tool used, the following filters can be applied to narrow down results:
* `contains(entity.name, "easytrade")`
* `contains(affected_entity.name, "easytrade")`
* `contains(container.name, "easytrade")`
For best results, you can combine these filters with an `OR` operator.
## Logs
To fetch logs for easytrade, execute `fetch logs | filter contains(container.name, "easyatrade")`.
For fetching just error-logs, add `| filter loglevel == "ERROR"`.
Environment Variables
Breaking Change in v1.0.0: The MCP server no longer automatically loads
.envfiles. To use environment variables from a.envfile, you need to configure your MCP client to load environment variables using the nativeenvFileconfiguration option. See the configuration examples below for details.
DT_ENVIRONMENT(required, string, e.g.,https://abc12345.apps.dynatrace.com) - URL to your Dynatrace Platform (do not use Dynatrace classic URLs likeabc12345.live.dynatrace.com)DT_PLATFORM_TOKEN(optional, string, e.g.,dt0s16.SAMPLE.abcd1234) - Dynatrace Platform TokenOAUTH_CLIENT_ID(optional, string, e.g.,dt0s02.SAMPLE) - Alternative: Dynatrace OAuth Client ID (for advanced use cases)OAUTH_CLIENT_SECRET(optional, string, e.g.,dt0s02.SAMPLE.abcd1234) - Alternative: Dynatrace OAuth Client Secret (for advanced use cases)DT_SSO_URL(optional, string, e.g.,https://sso.dynatrace.com) - Override the SSO URL for OAuth authentication. By default, the SSO URL is automatically discovered from your Dynatrace environment.DT_GRAIL_QUERY_BUDGET_GB(optional, number, default:1000) - Budget limit in GB (base 1000) for Grail query bytes scanned per session. The MCP server tracks your Grail usage and warns when approaching or exceeding this limit.
When just providing DT_ENVIRONMENT, the local MCP server will try to open a browser window to authenticate against the Dynatrace SSO.
For more information about the other authentication methods, please have a look at the documentation about creating a Platform Token in Dynatrace, as well as creating an OAuth Client in Dynatrace for advanced scenarios.
In addition, depending on the features you use, the following variables can be configured:
SLACK_CONNECTION_ID(string) - connection ID of a Slack Connection
Proxy Configuration
The MCP server honors system proxy settings for corporate environments:
https_proxyorHTTPS_PROXY(optional, string, e.g.,http://proxy.example.com:8080) - Proxy server URL for HTTPS requestshttp_proxyorHTTP_PROXY(optional, string, e.g.,http://proxy.example.com:8080) - Proxy server URL for HTTP requestsno_proxyorNO_PROXY(optional, string, e.g.,localhost,127.0.0.1,.local) - Comma-separated list of hostnames or domains that should bypass the proxy
Note: The no_proxy environment variable is currently logged for informational purposes but not fully enforced by the underlying HTTP client. If you need to bypass the proxy for specific hosts, consider configuring your proxy server to handle these exclusions.
Example configuration with proxy:
export HTTPS_PROXY=http://proxy.company.com:8080
export NO_PROXY=localhost,127.0.0.1,.company.local
export DT_ENVIRONMENT=https://abc12345.apps.dynatrace.com
Scopes for Authentication
Depending on the features you are using, the following scopes are needed:
Available for both Platform Tokens and OAuth Clients:
app-engine:apps:run- needed for almost all toolsautomation:workflows:read- read Workflowsautomation:workflows:write- create and update Workflowsautomation:workflows:run- run Workflowsapp-settings:objects:read- read app-settings - needed forsend_slack_messagetool to read connection details from App-Settingsstorage:buckets:read- needed forexecute_dqltool to read all system data stored on Grailstorage:logs:read- needed forexecute_dqltool to read logs for reliability guardian validationsstorage:metrics:read- needed forexecute_dqltool to read metrics for reliability guardian validationsstorage:bizevents:read- needed forexecute_dqltool to read bizevents for reliability guardian validationsstorage:spans:read- needed forexecute_dqltool to read spans from Grailstorage:entities:read- needed forexecute_dqltool to read Entities from Grailstorage:events:read- needed forexecute_dqltool to read Events from Grailstorage:security.events:read- needed forexecute_dqltool to read Security Events from Grailstorage:system:read- needed forexecute_dqltool to read System Data from Grailstorage:user.events:read- needed forexecute_dqltool to read User events from Grailstorage:user.sessions:read- needed forexecute_dqltool to read User sessions from Grailstorage:smartscape:read- needed forexecute_dqltool to read Smartscape Datastorage:events:write- needed forsend_eventtool to send event data to Dynatracedavis-copilot:conversations:execute- execute conversational skill (chat with Copilot)davis-copilot:nl2dql:execute- execute Davis Copilot Natural Language (NL) to DQL skilldavis-copilot:dql2nl:execute- execute DQL to Natural Language (NL) skilldavis:analyzers:read- needed for listing and getting Davis analyzer definitionsdavis:analyzers:execute- needed for executing Davis analyzersemail:emails:send- needed forsend_emailtool to send emailsdocument:documents:read- needed forlist_documentsandread_documenttools to list and read Dynatrace documents (Notebooks, Dashboards, Launchpads, etc.)document:documents:write- needed forcreate_documenttool to create new documents
Notes:
- Versions before 0.12.0 required the scope
app-engine:functions:run, which is no longer required. - Versions before 0.13.0 required the scopes
settings:objects:readandenvironment-api:entities:read, which are no longer required.
✨ Example prompts ✨
You can start with something as simple as "Is my component monitored by Dynatrace?", and follow up with more sophisticated examples.
Troubleshooting
Authentication Issues
In most cases, authentication issues are related to missing scopes or invalid tokens. Please ensure that you have added all required scopes as listed above.
For Platform Tokens:
- Verify your Platform Token has all the necessary scopes listed in the "Scopes for Authentication" section
- Ensure your token is valid and not expired
- Check that your user has the required permissions in your Dynatrace Environment
For OAuth Clients: In case of OAuth-related problems, you can troubleshoot SSO/OAuth issues based on our Dynatrace Developer Documentation.
It is recommended to test access with the following API (which requires minimal scopes app-engine:apps:run and, e.g., storage:logs:read):
- Use OAuth Client ID and Secret to retrieve a Bearer Token (only valid for a couple of minutes):
curl --request POST 'https://sso.dynatrace.com/sso/oauth2/token' \
--header 'Content-Type: application/x-www-form-urlencoded' \
--data-urlencode 'grant_type=client_credentials' \
--data-urlencode 'client_id={your-client-id}' \
--data-urlencode 'client_secret={your-client-secret}' \
--data-urlencode 'scope=app-engine:apps:run storage:logs:read'
- Use
access_tokenfrom the response of the above call as the bearer-token in the next call:
curl -X GET https://abc12345.apps.dynatrace.com/platform/management/v1/environment \
-H 'accept: application/json' \
-H 'Authorization: Bearer {your-bearer-token}'
- You should retrieve a result like this:
{
"environmentId": "abc12345",
"createTime": "2023-01-01T00:10:57.123Z",
"blockTime": "2025-12-07T00:00:00Z",
"state": "ACTIVE"
}
Problem accessing data on Grail
Grail has a dedicated section about permissions in the Dynatrace Docs. Please refer to https://docs.dynatrace.com/docs/discover-dynatrace/platform/grail/data-model/assign-permissions-in-grail for more details.
Telemetry
The Dynatrace MCP Server sends telemetry data using Dynatrace OpenKit BizEvents to help improve the product. This includes:
- Server start events (
com.dynatrace-oss.mcp.server-start) - Client initialization events (
com.dynatrace-oss.mcp.client-initialization) - which MCP client is connecting (e.g., VS Code, Claude Desktop, Cursor) - Tool usage events (
com.dynatrace-oss.mcp.tool-usage) - which tools are called, success/failure, execution duration - Error events (
com.dynatrace-oss.mcp.error) - error tracking for debugging and improvement
All telemetry data is sent as Business Events and is accessible via Grail for analysis:
fetch bizevents
| filter startsWith(event.type, "com.dynatrace-oss.mcp")
| sort timestamp DESC
Privacy and Opt-out:
- Telemetry is enabled by default but can be disabled by setting
DT_MCP_DISABLE_TELEMETRY=true - No sensitive data from your Dynatrace environment is tracked
- Only anonymous usage statistics and error information are collected
- Usage statistics and error data are transmitted to Dynatrace’s analytics endpoint
Configuration options:
DT_MCP_DISABLE_TELEMETRY(boolean, default:false) - Disable TelemetryDT_MCP_TELEMETRY_APPLICATION_ID(string, default:dynatrace-mcp-server) - Application ID for trackingDT_MCP_TELEMETRY_ENDPOINT_URL(string, default: Dynatrace endpoint) - OpenKit endpoint URLDT_MCP_TELEMETRY_DEVICE_ID(string, default: auto-generated) - Device identifier for tracking
To disable usage tracking, add this to your environment:
DT_MCP_DISABLE_TELEMETRY=true