# Nasdaq Data Link MCP for AI Agents AI Agent Connect > Nasdaq Data Link MCP connects your AI agent to professional-grade financial and economic datasets. You can query datatables, inspect schemas, and manage large-scale bulk downloads for CSV, Parquet, or ZIP files. It turns your AI into a research powerhouse for market analysis, economic indicators, and alternative data. ## Overview - **Category:** money-moves - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_JetgEjfNYXxZjBKgsK9Eqta1yhwzQLsEOPXl7Hq5/ai-agent-connect - **Tags:** financial-data, stock-market, economic-indicators, quandl, nasdaq ## Description This Connector bridges the gap between your AI agent and professional-grade financial data. Instead of manually scrubbing through websites or writing complex scripts to handle different API endpoints, you can just tell your agent what you need. You can pull historical prices, economic indicators, or alternative datasets using natural language. It handles the heavy lifting of filtering by ticker, date, or other specific criteria. If you need a massive dataset, it manages the bulk download process for you, letting you track progress and grab the final files in formats like Parquet or CSV. It's a massive time-saver for anyone who spends their day digging through numbers. By adding this to your Vinkius catalog, you're giving your agent a direct line to high-quality, structured data that's usually locked behind complicated authentication and pagination logic. ## Tools ### get_datatable_metadata Look up the schema, column types, and descriptions for any Nasdaq datatable. Use this to see what filters are available. ### request_bulk_download Start a bulk export for a specific datatable and get a status update. This is useful for getting large datasets. ### get_bulk_download_file Grab a specific file URL once a bulk export has finished processing. Use this to download your final data. ### get_datatable Fetch specific rows from a Nasdaq datatable using filters like ticker or date. This helps you get targeted data. ## Prompt Examples **Prompt:** ``` What's the metadata for the MER/F1 table? ``` **Response:** ``` I've pulled the metadata for MER/F1. This table holds fundamental financial data. You can filter by **ticker** and **date**. Key columns include: * `reportid` * `unitid` * `indicatorid` * `value` ``` **Prompt:** ``` Get the last 5 prices for MSFT from the WIKI/PRICES table. ``` **Response:** ``` I've pulled the latest 5 records for MSFT. On 2018-03-27, the close price was 89.47. Would you like me to pull more or export the full history? ``` **Prompt:** ``` Start a bulk download for the ZACKS/CP table. ``` **Response:** ``` I've started the bulk download for ZACKS/CP. The current status is **PENDING**. I'll keep an eye on it and let you know as soon as the file is ready for you to grab. ``` ## Capabilities ### Query unsorted datatables Fetch specific financial rows from a table using filters like ticker or date. ### Inspect table schemas Check column types and filterable fields before running your queries. ### Manage bulk downloads Initiate and monitor large dataset exports without crashing your session. ### Retrieve exported files Download processed files in CSV, Parquet, or ZIP formats once they are ready. ### Handle paginated results Navigate through large result sets using cursor-based pagination. ## Use Cases ### Pulling historical inflation data A researcher needs 10 years of inflation data. They ask the agent to find the economic indicator table and fetch the latest records. ### Correlating stock prices with commodities An analyst wants to see if a stock's price correlates with a specific commodity. They use get_datatable to pull both sets of data for a side-by-side comparison. ### Downloading massive alternative datasets A data scientist needs a 50GB dataset of alternative data. They use request_bulk_download to start the process and then check the status. ### Schema exploration before querying A quant needs to know what columns are available in a new dataset. They ask the agent to check the metadata before running any queries. ## Benefits - Stop writing API scripts by using get_datatable to fetch specific financial rows instantly. - Avoid guessing column names with get_datatable_metadata to see exactly what data is available. - Handle massive datasets easily with request_bulk_download to start large exports without crashing your session. - Get your data in the right format by using get_bulk_download_file to grab CSV, Parquet, or ZIP files. - Save time on data cleaning by using cursor-based pagination to navigate large results. ## How It Works The bottom line is you get direct, natural-language access to professional financial data without touching a single line of boilerplate code. 1. Connect your Nasdaq Data Link API key to the Connector. 2. Describe the specific dataset or ticker you need to your AI agent. 3. Receive the filtered data or a download link for the full export. ## Frequently Asked Questions **How does the Nasdaq Data Link MCP help with stock research?** It lets your AI agent pull historical prices and fundamental data directly into your conversation. You can ask for specific tickers or date ranges without having to navigate a complex web portal. **Can I use this Connector to download large datasets?** Yes, it includes a specific tool for bulk downloads. If a dataset is too large for a standard query, your agent can start a bulk export and notify you when the file is ready. **What kind of data can I get through this Connector?** You can access a wide range of professional data, including economic indicators, stock market prices, and alternative datasets provided by Nasdaq Data Link. **Does the Nasdaq Data Link MCP support different file formats?** Yes, it supports common formats like CSV, Parquet, and ZIP. Once a bulk download is processed, your agent can provide the direct link to the file. **How do I know what filters are available for a specific table?** You can ask your agent to check the metadata for any table. It will tell you which columns are filterable, such as ticker, date, or specific IDs, before you run your query. **Is this Connector good for quantitative research?** It's built for it. It's great for automating the retrieval of economic indicators and fundamental data that quants use as inputs for their models. **How can I filter a datatable for a specific ticker and date range?** Use the `get_datatable` tool and provide a JSON string in the `filters` parameter, such as `{"ticker": "AAPL", "date.gt": "2023-01-01"}`. This allows you to narrow down results precisely. **How do I check which columns are available in a dataset before querying it?** Run the `get_datatable_metadata` tool with the `vendor_code` and `table_code`. It will return the table's schema, including column names, types, and which fields support filtering. **What should I do if the dataset is too large for a standard query?** For very large datasets, use the `request_bulk_download` tool. This initiates an asynchronous export process. Once the status reaches 'SUCCEEDED', you can use `get_bulk_download_file` to retrieve the data.