Skip to main content
Glama
kaeljune

Fibaro HC3 MCP Server

by kaeljune

fibaro_run_scene

Execute a smart home scene on your Fibaro HC3 system by specifying the scene ID to automate lighting, devices, or routines.

Instructions

Run/start a scene

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesScene ID to run

Implementation Reference

  • MCP tool handler for fibaro_run_scene: extracts scene ID from arguments, calls FibaroClient.runScene, and returns success message.
    case 'fibaro_run_scene': {
      if (!this.fibaroClient) {
        throw new Error('Not connected to Fibaro HC3. Please check your configuration and restart the MCP server.');
      }
      const sceneId = args?.id as number;
      await this.fibaroClient.runScene(sceneId);
      return {
        content: [
          {
            type: 'text',
            text: `Successfully started scene ${sceneId}`,
          },
        ],
      };
    }
  • src/index.ts:301-313 (registration)
    Tool registration in ListTools response, including name, description, and input schema.
    {
      name: 'fibaro_run_scene',
      description: 'Run/start a scene',
      inputSchema: {
        type: 'object',
        properties: {
          id: {
            type: 'number',
            description: 'Scene ID to run',
          },
        },
        required: ['id'],
      },
  • FibaroClient helper method that performs the HTTP POST to start the scene via Fibaro API.
    async runScene(id: number): Promise<void> {
      try {
        await this.client.post(`/api/scenes/${id}/action/start`, {
          args: []
        });
      } catch (error) {
        throw new Error(`Failed to run scene ${id}: ${error}`);
      }
    }
  • Input schema definition for the fibaro_run_scene tool.
    inputSchema: {
      type: 'object',
      properties: {
        id: {
          type: 'number',
          description: 'Scene ID to run',
        },
      },
      required: ['id'],
    },

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kaeljune/fibaro-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server