appd-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APPD_LOG_LEVEL | No | Log level. | |
| APPD_TIMEOUT_MS | No | Timeout in milliseconds. | |
| APPD_ACCOUNT_NAME | Yes | Your tenant name. | |
| APPD_API_CLIENT_ID | Yes | OAuth API Client ID. | |
| APPD_TOOLS_ENABLED | No | Tools enabled configuration. | |
| APPD_CONTROLLER_URL | Yes | The AppDynamics Controller base URL. | |
| APPD_EVENTS_API_KEY | No | Only needed for appd_query_analytics_events. | |
| APPD_API_CLIENT_SECRET | Yes | OAuth API Client Secret. | |
| APPD_EVENTS_SERVICE_URL | No | Only needed for appd_query_analytics_events. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| appd_list_applicationsA | List business applications visible to the configured API Client. Optionally filter to apps that have been "alive" in the last N minutes (SaaS only). |
| appd_get_application_modelA | Fetch business transactions, tiers, nodes, and backends for one application in parallel. Anchor for nearly all RCA workflows. |
| appd_get_metric_hierarchyA | Walk the metric hierarchy for one application. Without metricPath returns top-level folders; with metricPath returns the children at that level. Cached for 5 minutes. |
| appd_query_metricsA | Fetch one or more metric paths over a time range using metric-data-v2. Defaults to BEFORE_NOW 30 minutes with rollup=true. Surfaces granularity and long-window warnings. |
| appd_get_transaction_snapshotsA | Retrieve slow/error/diagnostic transaction snapshots for an application. Default cap 100, hard max 600. Use needExitCalls=true to feed dependency-map analysis. |
| appd_get_health_rule_violationsA | Retrieve open / recently-closed health rule violations for an application within a time window. |
| appd_get_anomaly_violationsB | Retrieve anomaly violations for an application within a time window. Set fetchSuspectedCause=true to include the suspected-cause RCA payload (eventDetailMap.{id}.suspectedCauses[]). |
| appd_get_eventsB | Retrieve up to 600 events for an application by type and severity within a time window. |
| appd_list_health_rulesB | List health rule summaries (id, name, enabled) for an application via the Alerting REST v1 API. Optionally fan out to fetch full rule definitions. |
| appd_get_alerting_configA | Composite read: parallel-fetches health rules + policies + actions + schedules for one application via the Alerting REST v1 API. Use this for "what alerts and to whom" inventories. |
| appd_query_analytics_eventsA | Run an ADQL query against the Events Service. Mode A: single ADQL string. Mode B: array of ≤20 query objects. Requires APPD_EVENTS_SERVICE_URL and APPD_EVENTS_API_KEY to be configured. |
| appd_get_dependency_mapB | Synthesize a tier→tier/backend dependency map from the application model + transaction snapshots (with exit calls). MCP-level aggregation — confidence depends on snapshot density (warning surfaces when sparse). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool targets a distinct AppDynamics resource or function (e.g., alerting config, anomaly violations, application model, dependency map, events, health rule violations, metric hierarchy, transaction snapshots, applications list, health rules list, analytics events, metrics query). No overlapping purposes; descriptions clearly differentiate the tools.
All tools follow a consistent 'appd_verb_noun' pattern in snake_case. Verbs are predominantly 'get', 'list', or 'query', applied appropriately to each operation. The naming is predictable and aids agent selection.
12 tools is well-scoped for an AppDynamics monitoring server. The set covers essential monitoring and RCA workflows without being overwhelming. Each tool serves a clear purpose and earns its place.
The tool surface covers key monitoring operations: application discovery, model, health rule violations, anomaly violations, events, metrics, transaction snapshots, dependencies, alerting config, health rules, metric hierarchy, and analytics events. Minor gaps exist (e.g., no tool for dashboard retrieval or detailed health rule by ID), but core workflows are fully supported.