Spot AI MCP (Unofficial)

io.github.phil-bryant由 GitHub 账号 phil-bryant 发布v0.3.0更新于 Oct 24, 2026

Unofficial community MCP server for the Spot AI camera and video-intelligence REST API. Read-only.

发布方自己的服务：Spot

已验证STDIO仅桌面安全与监控数据与分析

服务详情

标识符: io.github.phil-bryant/spot-ai-mcp
传输: STDIO
运行时: Desktop only
信任: Verified
发布于: Sep 16, 2026

安全提示

MCP 服务会接收对话中的工具调用请求，并可能执行外部操作。启用前请先了解该服务能做什么，并只授予它所需的权限。

注册中心已验证此条目所属的 GitHub 账号 phil-bryant。这并不表明该账号就是产品方。

SourceWeft 的检查只涵盖条目是否完整、端点是否响应；不审查服务器的代码，也不审查其工具的行为。

在 README 中添加徽章

向读者展示该 MCP 服务已收录于 SourceWeft，徽章链接到本页。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.phil-bryant%2Fspot-ai-mcp.svg)](https://sourceweft.com/mcp/io.github.phil-bryant%2Fspot-ai-mcp?utm_source=readme&utm_medium=badge)

概览

AI 生成的概览

非官方的 Spot AI 摄像头与视频智能 REST API 只读 MCP 服务器，让助手浏览摄像头、区域和智能分析报告。

可以做什么: 列出位置、摄像头、单个摄像头详情和已启用摄像头数量，以及录像设备
查看某台摄像头上定义的区域
按日期范围获取人员、车辆或叉车的计数、闲置与在场事件
获取车牌识别摄像头的车牌识别报告
为最多四台摄像头生成实时视频观看链接
通过通用接口调用任意已文档化的 v1 或 v2 GET 路径
适用场景: 适合让助手回答关于 Spot AI 摄像头部署的问题，例如有哪些摄像头及其位置、某段时间内的活动统计、车牌读取记录，或获取实时画面链接，同时不授予其对组织的写入权限。
运行要求: 以 Python 3.9+ 包通过 stdio 在本地运行（uvx 或 pip install spot-ai-mcp，或 python3 -m spot_ai_mcp）。需要将 Spot AI API 密钥放入 SPOT_AI_API_KEY 环境变量，也可选用通过 SPOT_AI_OP_BIN、SPOT_AI_OP_ITEM 和 SPOT_AI_OP_FIELD 变量配置的密钥获取命令。需要能访问 Spot AI API 的网络。

安装前请注意

需要 Spot AI API 密钥，且必须在控制台为其添加授权角色，否则各资源接口会返回空列表。密钥以 bearer 令牌形式发送给 Spot AI API。服务器设计为只读，但有一个工具会发出 POST 请求以生成实时观看链接，通用 GET 接口可访问任意已文档化的 API 路径。该服务器为非官方项目，与 Spot AI 无隶属关系。

安装

在 SourceWeft 中

打开控制台中的 Spot AI MCP (Unofficial)，将其添加到工作区。
为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照仓库中的启动说明。

README

spot-ai-mcp

Unofficial community MCP server for the Spot AI camera / video-intelligence REST API. Not affiliated with or endorsed by Spot AI.

Single-file, stdio transport, no dependencies beyond Python 3.9+. Read-only by design: it can browse cameras and intelligence data but can never modify anything in your Spot AI org. Every tool wraps a GET endpoint except get_live_stream_urls, which wraps POST /v1/cameras/live — a read-like POST that only generates a viewing URL. All tools declare the readOnlyHint: true MCP annotation.

Install

or pip install spot-ai-mcp, or run straight from a checkout with python3 -m spot_ai_mcp (no dependencies to install).

API key

Create a key in the Spot AI dashboard's API settings, then add an authorization (a role, e.g. Owner, optionally scoped) on the key's settings page. A key without a role returns empty lists from every resource endpoint while get_camera_count still works — that's the tell.

The server resolves the key lazily on the first API call:

SPOT_AI_API_KEY environment variable — the normal path.
Optionally, a secret-helper command, so the key never sits in an env var or config: the server runs $SPOT_AI_OP_BIN -f $SPOT_AI_OP_ITEM $SPOT_AI_OP_FIELD (defaults 1psa -f spot.ai api_key, per 1psa, a vault-scoped 1Password service-account CLI). Point these at any command with the same flag convention.

The key is never written to disk or config by this server.

Tools

Tool	What it does
`list_locations`	Locations the key can see (paginated)
`list_cameras`	Cameras with status, location, IP, MAC (paginated)
`get_camera`	One camera by id
`get_camera_count`	Number of enabled cameras in the org
`list_appliances`	Intelligent Video Recorders (paginated)
`get_zones`	Zones defined on a camera
`get_intelligence`	Counting / idle / presence events for people, vehicles, or forklifts over a date range
`get_lpr_report`	License-plate-recognition report for an LPR camera
`get_live_stream_urls`	Live-stream viewing URL for up to 4 cameras
`spot_api_get`	Escape hatch: GET any documented `/v1/` or `/v2/` path

Notes

Dual-era MCP server: speaks both the modern per-request protocol (server/discover, spec 2026-07-28) and the legacy initialize handshake (2024-11-05 through 2025-06-18), so old and new clients both work.
Base URL is https://dev-api.spot.ai, auth is Authorization: Bearer <key>.
Cloudflare in front of the API rejects Python's default user agent with error 1010; the server sends User-Agent: spot-ai-mcp/<version>.
Endpoint index: https://developers.spot.ai/llms.txt (append .md to any docs URL for markdown, including the OpenAPI definition per endpoint).