Cartrack Fleet MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_SHEET_ID | Yes | The ID of the 'Procon Fleet — Live Dashboard' Google Sheet (the long string in its URL). | |
| CARTRACK_BASE_URL | Yes | The base URL for your country's Cartrack API host, e.g. https://fleetapi-za.cartrack.com/rest. Confirm which host serves your fleet. | |
| CARTRACK_PASSWORD | Yes | Your Cartrack API password, generated from Fleetweb -> Settings -> API Settings. | |
| CARTRACK_USERNAME | Yes | Your Cartrack API username, generated from Fleetweb -> Settings -> API Settings. | |
| GOOGLE_EXPORT_FOLDER_ID | No | Optional. Drive folder ID where the monthly .xlsx export of the live Google Sheet will be uploaded. | |
| GOOGLE_SERVICE_ACCOUNT_JSON | Yes | Path to the Google service account JSON key file. (If adapting to read key contents directly, use GOOGLE_SERVICE_ACCOUNT_JSON_CONTENTS instead.) | |
| MASTER_WORKBOOK_DRIVE_FILE_ID | No | Optional. Drive file ID of the master 'Procon Electrical & Steel Fleet Fuel Tracking System' workbook, required for monthly reconciliation. |
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 |
|---|---|
| list_vehiclesA | Full Procon fleet vehicle list from Cartrack: registration numbers, vehicle IDs, make/model, and maintenance status. No filtering by default — returns the whole fleet (auto-paginated). Use this to match against the Fleet Register. |
| get_vehicle_statusA | Current status and last-known location for the fleet (or one vehicle): ignition, speed, idling, odometer, fuel level, and GPS position. This is a live snapshot, not history — there is no date range. Rate-limited to 60 requests/minute by Cartrack. |
| get_tripsA | Trip history for a date range: route (start/end location and coordinates), distance, duration, idle time, and driving behavior (harsh braking/cornering/acceleration, speeding events). Defaults to the previous 24 hours. Cartrack caps each request at 31 days — longer ranges are chunked automatically. Fleet-wide queries cannot be filtered by vehicle at the API level (Cartrack has no such filter on the fleet-wide endpoint); pass |
| get_fuel_dataA | Fuel level and consumption for a date range, fleet-wide or for one vehicle. Defaults to the previous 24 hours. When no |
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 4 tools
Each tool targets a distinct resource and data type: live vehicle status, the full vehicle list, trip history, and fuel data. No overlap or ambiguity between them.
Names mostly follow a get_/list_ + resource pattern, with list_vehicles being the only deviation from the get_ prefix. This is predictable and easy to navigate.
Four tools is well-scoped for a fleet data retrieval server. Each tool covers a meaningful slice of the domain without unnecessary bloat or overlap.
The core fleet data surface is covered: vehicle inventory, live status, trip history, and fuel consumption. Minor gaps exist such as driver details or location history, but nothing that blocks primary workflows.