What are the runtime requirements?
Node.js and npm are required to build and run the server after cloning the repository.
@MCP-Mirror
基本信息
Mirror of
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A Model Context Protocol (MCP) server that provides tools to control and monitor Home Assistant devices through MCP-enabled applications.
Clone the repository, install dependencies with npm install, build with npm run build, then configure the MCP server in your settings file (e.g., claude_desktop_config.json) by setting the command to node, args to the built index.js, and env variables HA_URL and HA_TOKEN. Use the provided tools (get_state, toggle_entity, trigger_automation, list_entities) from any MCP client.
Node.js and npm are required to build and run the server after cloning the repository.
Set the `HA_URL` and `HA_TOKEN` environment variables when configuring the MCP server. Replace with your Home Assistant instance URL and a long-lived access token.
It connects directly to your Home Assistant instance via the provided URL and access token. All data resides on that instance.
The server uses the MCP protocol over stdio; authentication is handled via a Home Assistant long-lived access token passed in the `HA_TOKEN` environment variable.

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai
Model Context Protocol (MCP) server for Hostinger API. If you don't want to install or run anything locally, connect directly to Hostinger's hosted MCP server: This opens a browser window to authorize via OAuth. Once app
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi
Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the resu
评论