Safie API MCP Server

@SafiePublic

代码仓库

基本信息

分类

开发工具

许可证

MIT license

传输方式

stdio

作者

SafiePublic

关于 Safie API MCP Server

MCP server that enables AI Agents to use images and events from Safie camera devices

#safie-api#mcp-server #ai-agents

Safie API MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "safie-api-mcp-server": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "safie-api-mcp-server",
        "."
      ]
    }
  }
}

Safie API MCP Server 工具

デバイス一覧を取得します

指定されたデバイスから画像を取得します

指定されたデバイスで録画されている映像（メディア）の一覧を取得します

指定されたデバイスの現在のGPS位置情報を取得します

指定されたデバイスの最新サムネイルを取得します

指定されたデバイスの標準イベント情報一覧を取得します

概览

What is Safie API MCP Server?

An MCP (Model Context Protocol) server that uses the Safie API to retrieve device information and perform operations. It is a preview release offering experimental access to a subset of Safie device functionality.

How to use Safie API MCP Server?

Requires Python 3.10+ with uv or Docker. Set either the ACCESS_TOKEN environment variable (OAuth2 access token) or API_KEY (API key). Configure in Claude Desktop by adding the server to mcpServers in the client settings, using either uv run or a Docker image built from the repository.

Key features of Safie API MCP Server

List devices registered on the Safie platform.
Capture an image from a specified device.
List recorded video media for a device.
Get the current GPS location of a device.
Retrieve the latest thumbnail for a device.
List standard event information for a device.

Use cases of Safie API MCP Server

Querying device status and location during AI‑powered conversations.
Pulling live snapshots or recent media from surveillance cameras.
Integrating Safie device data into workflows via Claude Desktop.

常见问题

Is this server production‑ready?

No, this implementation is a preview version that only offers a limited set of features experimentally. It is not officially supported.

What runtime dependencies are required?

Python 3.10 or later, and either `uv` or Docker to run the server.

How do I authenticate with the Safie API?

Set the environment variable `ACCESS_TOKEN` (OAuth2 access token) or `API_KEY` (API key). If both are set, `ACCESS_TOKEN` takes precedence.

What tools are available?

Six tools: `list_devices`, `get_device_image`, `list_device_media`, `get_device_location`, `get_device_thumbnail`, and `list_device_standard_events`.

Are there any known limitations?

The server is a preview; only a subset of Safie API capabilities is exposed, and support is not provided. Data handling follows standard MCP transport (stdio) and authentication via environment variables.

开发工具分类下的更多 MCP 服务器

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Ramen

bkraad47

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott