Adjust MCP server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ADJUST_API_TOKEN | Yes | Required. The API token of your Adjust user. It is a bearer credential with that user's reporting access. | |
| ADJUST_APP_TOKENS | Yes | Required. Comma-separated app tokens this server may read, up to 200. Every request is checked against this list, and app discovery returns only these apps. | |
| ADJUST_ENVIRONMENT | No | `production` (default) or `sandbox`. Fixed for every report; a tool call cannot change it. | production |
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
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| adjust_list_appsA | List the Adjust applications in ADJUST_APP_TOKENS that this API token can read, with native currency and configured operating systems. Applications outside the allowlist are never returned. |
| adjust_list_eventsA | Discover native event base slugs, ordinary activity-count metric IDs and app-specific event tokens for one allowlisted Adjust app. Use activityMetric for counts; the event base slug alone is not a report metric. Keep SKAdNetwork and aggregate revenue definitions separate. |
| adjust_get_catalogA | Read documented standard Adjust dimensions and example metrics, plus event metrics scoped to one allowlisted application. Metrics and spend/revenue access remain subject to Adjust permissions; the standard metric list is not exhaustive. |
| adjust_run_reportA | Read an attribution/performance report for one allowlisted Adjust app. Preserves native totals, warnings, attribution options, currency and UTC offset. Missing metrics are null; ratios are native fractions. A truncated or partial result is not a complete extraction. |
| adjust_compare_periodsA | Compare two equal-length periods for one allowlisted Adjust application with identical metrics, filters, OS and measurement settings. Defaults to the immediately preceding period. Changes use native totals, never sums of breakdowns. Unavailable or partial values have no calculated change; cohort maturity and reporting delays still apply. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| adjust-guide | How to read Adjust reports with this server: tool order, scope, measurement settings and rate limits. |
TDQS
Scored across 5 tools
Most tools target clearly different operations: listing apps, discovering events, reading a catalog, running a report, and comparing periods. The main overlap is between adjust_list_events and adjust_get_catalog, since both expose event metric information for one app, though their descriptions distinguish discovery tokens from catalog definitions.
All tool names consistently use the adjust_ prefix followed by a clear verb_noun pattern: list_apps, list_events, get_catalog, run_report, compare_periods. The convention is predictable throughout.
Five tools is well-scoped for a focused Adjust reporting server. Each tool supports a distinct stage of the analytics workflow without obvious redundancy.
The surface covers the core read-only analytics lifecycle: discovering apps, events, metrics/dimensions, running reports, and comparing periods. Minor gaps may exist around other Adjust resources or specialized report modes, but agents can accomplish the main workflows.