MCP Avantage

Instructions

Implementation Reference

• src/index.ts:1073-1087 (registration)

  Registers the 'technicalIndicators_kama' MCP tool, providing name, description, input validation schema, and a thin execute handler that invokes the generic executeAvantageTool helper with the specific Alpha Vantage library method.
  server.addTool({ name: "technicalIndicators_kama", description: "Kaufman Adaptive Moving Average (KAMA)", parameters: schemas.TechnicalIndicatorsTimeSeriesIndicatorParamsSchema, execute: ( args, context // Let type be inferred ) => executeAvantageTool( "technicalIndicators_kama", args, context, (av, params) => av.technicalIndicators.kama(params) ), });
• src/schemas.ts:204-215 (schema)

  Defines the Zod input schema used by the tool: common parameters (symbol, interval, etc.) extended with time_period and series_type for Kaufman Adaptive Moving Average calculation.
  export const TechnicalIndicatorsCommonIndicatorParamsSchema = z.object({ symbol: z.string().describe('The stock symbol (e.g., "IBM").'), interval: z.string().describe('Time interval (e.g., "daily", "60min", "weekly"). Check Alpha Vantage docs for valid intervals per indicator.'), datatype: DatatypeSchema.default('json').optional(), month: z.string().optional().describe('Specific month for intraday intervals (YYYY-MM format).'), }).describe('Common parameters for many technical indicators.') // Schema for indicators requiring time_period and series_type export const TechnicalIndicatorsTimeSeriesIndicatorParamsSchema = TechnicalIndicatorsCommonIndicatorParamsSchema.extend({ time_period: z.string().describe('Number of data points used to calculate the indicator.'), // Using string as AV API expects string series_type: SeriesTypeSchema, }).describe('Parameters for time series based technical indicators.')
• src/index.ts:38-115 (helper)

  Core helper function for executing Alpha Vantage tools. Manages API authentication, client instance pooling via resource manager, invokes the specific library method (e.g., av.technicalIndicators.kama), handles responses and errors, returning JSON stringified data.
  async function executeAvantageTool<TArgs, TResult>( toolName: string, args: TArgs, context: Context<Record<string, unknown> | undefined>, // Use the imported Context type directly avantageMethod: ( av: AVantage, args: TArgs ) => Promise<{ error?: boolean; reason?: string; data?: TResult }> ): Promise<string> { logger.info(`Executing '${toolName}' tool for request ID: ${context}`); logger.debug(`Args for ${toolName}: ${JSON.stringify(args)}`); // --- Authentication & Resource Management --- // Access extraArgs safely - it might be null or undefined const extraArgsApiKey = context.extraArgs?.apiKey as string | undefined; const apiKey = extraArgsApiKey || config.apiKey; if (!apiKey) { logger.error(`'${toolName}' failed: Alpha Vantage API key missing.`); throw new UserError(apiKeyErrorMessage); } logger.debug( `Using AV API key (source: ${extraArgsApiKey ? "extraArgs" : "environment"}) for ${toolName}` ); try { // Get or create AVantage instance managed by ResourceManager const av = await resourceManager.getResource<AVantage>( apiKey, // Cache key is the resolved API key "avantage_client", // Type identifier for logging async (key) => { // Factory Function logger.info( `Creating new AVantage instance for key ending ...${key.slice(-4)}` ); // AVantage library reads AV_PREMIUM from process.env internally return new AVantage(key); }, async (avInstance) => { // Cleanup Function (no-op needed for AVantage) logger.debug(`Destroying AVantage instance (no-op)`); } ); // --- Library Call --- const result = await avantageMethod(av, args); // --- Response Handling --- if (result.error) { logger.warn( `'${toolName}' failed. Reason from avantage: ${result.reason}` ); throw new UserError(result.reason || `Tool '${toolName}' failed.`); } if (result.data === undefined || result.data === null) { logger.warn(`'${toolName}' completed successfully but returned no data.`); return "null"; // Return string "null" for empty data } logger.info(`'${toolName}' completed successfully.`); // Stringify the data part of the response return JSON.stringify(result.data); } catch (error: any) { logger.error( `Error during execution of '${toolName}': ${error.message}`, error ); // If it's already a UserError, rethrow it if (error instanceof UserError) { throw error; } // Otherwise, wrap it in a UserError throw new UserError( `An unexpected error occurred while executing tool '${toolName}': ${error.message}` ); } }