经 AI Skill Hub 精选评估,物联网工具 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
物联网工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
物联网工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/thingctx/thingctx
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"-----": {
"command": "npx",
"args": ["-y", "thingctx"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 物联网工具 执行以下任务... Claude: [自动调用 物联网工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"_____": {
"command": "npx",
"args": ["-y", "thingctx"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
One standard description, and your model can read context from and take actions on a real device, sensor, tool, or service, directly. No per-integration server.
thingctx uses the W3C Web of Things standard as a uniform interface between an AI application and the systems it needs to reach. Point it at a Thing Description and it drives the actual Thing the description names, over that Thing's own transport. The description is how you integrate; the device or service is what you act on. The integration is a document, not a server you run.
A "Thing" here is anything with a callable interface, not just hardware: a sensor or a robot, but equally a REST API, a database, a SaaS product, an internal service. A Thing Description (TD) is plain JSON that names that system's actions (things to do), properties (state to read or write), and events (things to subscribe to), plus the transport for each (HTTP, MQTT, local, and more). thingctx reads it, hands the actions to your model as tools, and calls each against the real system over the transport the TD names. The system's own endpoints are the server; you write nothing on the server side.
A whole TD can be this small (a weather API, no hardware in sight):
{
"@context": "https://www.w3.org/2022/wot/td/v1.1",
"id": "urn:example:weather:v1",
"title": "Weather",
"securityDefinitions": { "bearer_sc": { "scheme": "bearer" } },
"security": ["bearer_sc"],
"properties": {
"temperature": { "type": "number", "readOnly": true,
"forms": [{ "href": "https://api.example.com/temp" }] }
},
"actions": {
"forecast": {
"input": { "type": "object", "properties": { "city": { "type": "string" } } },
"forms": [{ "href": "https://api.example.com/forecast", "htv:methodName": "POST" }]
}
}
}
That document is the integration. Point an agent at it:
import thingctx
host = await thingctx.from_url("https://api.example.com/.well-known/wot")
print(await host.chat("what's the forecast for Cairo, and the current temperature?"))
The model picks the actions; thingctx routes each to its transport.
```bash pip install thingctx[all] # litellm + httpx + paho-mqtt + jsonschema + mcp
高质量开源MCP工具,易于使用
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:物联网工具 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | thingctx |
| Topics | mcpagent-toolsai-agentsjson-ld |
| GitHub | https://github.com/thingctx/thingctx |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-06-13 · 更新时间:2026-06-13 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端