rr_get_demand_forecast

Generate demand forecasts for inventory items to predict future sales and optimize stock levels, helping prevent stockouts and overstocking.

Instructions

Get demand forecast stats for an item

Input Schema

TableJSON Schema

Name	Required	Description	Default
`sku`	No
`item_id`	No
`window_days`	No
`store_id`	No

Implementation Reference

src/index.ts:28-28 (registration)

Tool registration: defines 'rr_get_demand_forecast' with name, description, and inputSchema in the TOOLS array

{ name: 'rr_get_demand_forecast', description: 'Get demand forecast stats for an item', inputSchema: { type: 'object' as const, properties: { sku: { type: 'string' }, item_id: { type: 'string' }, window_days: { type: 'number' }, store_id: { type: 'string' } } } },

src/index.ts:28-28 (schema)

Input schema for rr_get_demand_forecast: defines optional parameters (sku, item_id, window_days, store_id) as object properties

{ name: 'rr_get_demand_forecast', description: 'Get demand forecast stats for an item', inputSchema: { type: 'object' as const, properties: { sku: { type: 'string' }, item_id: { type: 'string' }, window_days: { type: 'number' }, store_id: { type: 'string' } } } },

src/index.ts:57-74 (handler)

callApi function: the handler that executes tool logic by making POST requests to the ReplenishRadar API endpoint with tool name and input parameters

async function callApi(toolName: string, input: Record<string, unknown>): Promise<unknown> {
  const resp = await fetch(`${BASE_URL}/api/mcp/call`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': `Bearer ${API_KEY}`,
    },
    body: JSON.stringify({ tool: toolName, input }),
  });

  if (!resp.ok) {
    const errorBody = await resp.text();
    throw new Error(`API error ${resp.status}: ${errorBody}`);
  }

  const data = await resp.json();
  return data.result;
}

src/index.ts:86-100 (handler)

CallToolRequestSchema handler: processes incoming tool calls by extracting name and arguments, invoking callApi, and returning formatted results

server.setRequestHandler(CallToolRequestSchema, async (request) => {
  const { name, arguments: args } = request.params;
  try {
    const result = await callApi(name, (args as Record<string, unknown>) || {});
    return {
      content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
    };
  } catch (error) {
    const message = error instanceof Error ? error.message : String(error);
    return {
      content: [{ type: 'text', text: `Error: ${message}` }],
      isError: true,
    };
  }
});

replenishradar