spot-ai-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SPOT_AI_OP_BIN | No | Secret-helper command binary. Defaults to '1psa'. | |
| SPOT_AI_API_KEY | No | Spot AI API key. Normal path for authentication. If not set, the server falls back to the secret-helper command. | |
| SPOT_AI_OP_ITEM | No | Secret-helper item. Defaults to 'spot.ai'. | |
| SPOT_AI_OP_FIELD | No | Secret-helper field. Defaults to 'api_key'. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_locationsA | List locations (id and name) the API key has access to. Paginated: pass the response's 'next' value back as 'cursor' until it is null. |
| list_camerasA | List cameras for the org (id, name, status, location, IP, MAC, appliance). Paginated via cursor. |
| get_cameraB | Get details for a single camera by id. |
| get_camera_countA | Get the number of enabled cameras in the organization. |
| list_appliancesB | List appliances (Intelligent Video Recorders) for the org. Paginated via cursor. |
| get_zonesB | List the zones defined on a camera. |
| get_intelligenceA | Get intelligence events and summary for a camera: counting, idle, or presence of people, vehicles, or forklifts over a date range. |
| get_lpr_reportB | Get the license-plate-recognition report for an LPR-enabled camera. |
| get_live_stream_urlsA | Get a URL to a live stream of up to 4 cameras. Generates a viewing URL for the authenticated caller; modifies nothing. |
| spot_api_getA | Escape hatch: perform a GET against any documented Spot AI API path (https://developers.spot.ai/llms.txt lists them). Example path: /v1/integrations. Only GET is supported; this server is read-only. |
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 10 tools
Most tools target clearly distinct resources and actions (locations, cameras, appliances, zones, intelligence, LPR). The main overlaps are get_camera_count versus list_cameras (count is derivable) and spot_api_get, which by design overlaps with everything as an escape hatch, but it is explicitly framed as a generic fallback.
Nine of ten tools follow a clean verb_noun pattern (list_locations, get_camera, get_zones, etc.) using get_/list_ prefixes. The single outlier is spot_api_get, which uses a noun_verb ordering, a minor deviation.
Ten tools is well within the ideal range and each one covers a distinct read operation. No redundant or filler tools; the set is tightly scoped to a read-only camera/security API.
The surface covers the core domain: locations, cameras, appliances, zones, intelligence events, LPR, and live streams. Minor gaps exist (no get_location or get_appliance detail), but the spot_api_get escape hatch lets agents reach any documented endpoint, mitigating dead ends.