Skip to main content
Glama
matteoantoci

Marketstack MCP Server

by matteoantoci

get_end_of_day_data

Retrieve end-of-day stock market data for specified tickers, filter by exchange, date range, and sort. Supports up to 100 symbols per request, pagination, and exact date/time queries for precise analysis.

Instructions

Obtain end-of-day data for one or multiple stock tickers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
date_fromNoFilter results based on a specific timeframe by passing a from-date in `YYYY-MM-DD` format. You can also specify an exact time in ISO-8601 date format, e.g. `2020-05-21T00:00:00+0000`.
date_toNoFilter results based on a specific timeframe by passing an end-date in `YYYY-MM-DD` format. You can also specify an exact time in ISO-8601 date format, e.g. `2020-05-21T00:00:00+0000`.
exchangeNoFilter your results based on a specific stock exchange by specifying the MIC identification of a stock exchange. Example: `XNAS`
limitNoSpecify a pagination limit (number of results per page) for your API request. Default limit value is `100`, maximum allowed limit value is `1000`.
offsetNoSpecify a pagination offset value for your API request. Example: An offset value of `100` combined with a limit value of 10 would show results 100-110. Default value is `0`, starting with the first available result.
sortNoBy default, results are sorted by date/time descending. Use this parameter to specify a sorting order. Available values: `DESC` (Default), `ASC`.DESC
symbolsYesSpecify one or multiple comma-separated stock symbols (tickers) for your request, e.g. `AAPL` or `AAPL,MSFT`. Each symbol consumes one API request. Maximum: 100 symbols

Implementation Reference

  • The async handler function that executes the tool logic: destructures input params, builds API request for Marketstack EOD endpoint, fetches data, and returns it or throws error.
    const getEndOfDayDataHandler = async (input: Input, client: MarketstackClient): Promise<Output> => {
      try {
        const { symbols, exchange, sort, date_from, date_to, limit, offset } = input;
    
        const apiRequestParams: MarketstackApiParams = {
          endpoint: 'eod',
          symbols,
          ...(exchange && { exchange }), // Include if exchange is provided
          ...(sort && { sort }), // Include if sort is provided
          ...(date_from && { date_from }), // Include if date_from is provided
          ...(date_to && { date_to }), // Include if date_to is provided
          ...(limit && { limit }), // Include if limit is provided
          ...(offset && { offset }), // Include if offset is provided
        };
    
        const data = await client.fetchApiData(apiRequestParams);
    
        return data;
      } catch (error: unknown) {
        console.error('getEndOfDayData tool error:', error);
        const message = error instanceof Error ? error.message : 'An unknown error occurred.';
        throw new Error(`getEndOfDayData tool failed: ${message}`);
      }
    };
  • Zod schema defining the input shape for the tool, including parameters like symbols, exchange, sort, date_from, date_to, limit, offset with descriptions and validations.
    const getEndOfDayDataInputSchemaShape = {
      symbols: z
        .string()
        .describe(
          'Specify one or multiple comma-separated stock symbols (tickers) for your request, e.g. `AAPL` or `AAPL,MSFT`. Each symbol consumes one API request. Maximum: 100 symbols'
        ),
      exchange: z
        .string()
        .optional()
        .describe(
          'Filter your results based on a specific stock exchange by specifying the MIC identification of a stock exchange. Example: `XNAS`'
        ),
      sort: z
        .enum(['DESC', 'ASC'])
        .optional()
        .default('DESC')
        .describe(
          'By default, results are sorted by date/time descending. Use this parameter to specify a sorting order. Available values: `DESC` (Default), `ASC`.'
        ),
      date_from: z
        .string()
        .optional()
        .describe(
          'Filter results based on a specific timeframe by passing a from-date in `YYYY-MM-DD` format. You can also specify an exact time in ISO-8601 date format, e.g. `2020-05-21T00:00:00+0000`.'
        ),
      date_to: z
        .string()
        .optional()
        .describe(
          'Filter results based on a specific timeframe by passing an end-date in `YYYY-MM-DD` format. You can also specify an exact time in ISO-8601 date format, e.g. `2020-05-21T00:00:00+0000`.'
        ),
      limit: z
        .number()
        .int()
        .min(1)
        .max(1000)
        .optional()
        .default(100)
        .describe(
          'Specify a pagination limit (number of results per page) for your API request. Default limit value is `100`, maximum allowed limit value is `1000`.'
        ),
      offset: z
        .number()
        .int()
        .min(0)
        .optional()
        .default(0)
        .describe(
          'Specify a pagination offset value for your API request. Example: An offset value of `100` combined with a limit value of 10 would show results 100-110. Default value is `0`, starting with the first available result.'
        ),
      // Note: The documentation also mentions /eod/[date] and /eod/latest, but the parameters section
      // seems to describe the /eod endpoint with query parameters. We'll implement the query parameter
      // approach for now as it's more flexible for date ranges.
    };
  • MCP server registration of the get_end_of_day_data tool, using the tool definition's name, description, input schema, and wrapped handler.
    server.tool(
      getEndOfDayDataTool.name,
      getEndOfDayDataTool.description,
      getEndOfDayDataTool.inputSchemaShape,
      wrapToolHandler((input) => getEndOfDayDataTool.handler(input, client))
    );
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure but provides minimal information. It doesn't mention whether this is a read-only operation, what permissions might be required, rate limits, or what format the data returns. The description only states what data is obtained without behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that immediately communicates the core purpose. There's no wasted language or unnecessary elaboration, making it perfectly concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what 'end-of-day data' includes (closing prices, volume, etc.), doesn't mention the return format, and provides no behavioral context despite the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the input schema comprehensively documents all 7 parameters. The description adds no additional parameter information beyond what's already in the schema, so it meets the baseline expectation but doesn't provide extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('obtain') and resource ('end-of-day data for one or multiple stock tickers'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this tool from sibling tools like 'get_intraday_data' or 'get_ticker_details' beyond the 'end-of-day' qualifier.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With multiple sibling tools for financial data (get_intraday_data, get_ticker_details, get_dividends_data, etc.), there's no indication of what distinguishes end-of-day data from other data types or when this specific tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

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/matteoantoci/mcp-marketstack'

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