Nasdaq Data Link

Provides MCP tools to query Nasdaq Data Link datasets, export data, and metadata through LLM-enabled workflows.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "stefanoamorelli-nasdaq-data-link-mcp": {
      "command": "mcp",
      "args": [
        "dev",
        "nasdaq_data_link_mcp_os/server.py",
        "--env-file",
        ".env"
      ],
      "env": {
        "PYTHONPATH": "/path/to/your/local/cloned/repo/nasdaq-data-link-mcp",
        "NASDAQ_DATA_LINK_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run Nasdaq Data Link as an MCP server to expose datasets and data actions to compatible clients. It provides convenient tools to search datasets, fetch data, retrieve metadata, list databases, and export data, all accessible through your preferred MCP client and natural language workflows.

How to use

You connect with an MCP client and point it at the Nasdaq Data Link MCP server you run on your machine or in your environment. Once connected, you can use natural language prompts or direct tool calls to perform common data tasks. You have five core tools at your disposal that work across Nasdaq Data Link databases: search datasets, get dataset, get dataset metadata, list databases, and export dataset. Use these tools to locate datasets by keyword, retrieve data with optional date ranges, inspect dataset structures, enumerate available databases, and export results in formats like JSON, CSV, or XML. Typical interactions include asking for GDP data, pulling stock history, or exporting a specific dataset for further analysis.

How to install

Prerequisites: you need Python 3.13 or newer and the MCP CLI tooling available in your environment.

Clone the repository and enter the project directory.

git clone https://github.com/stefanoamorelli/nasdaq-data-link-mcp.git
cd nasdaq-data-link-mcp

Initialize MCP and add the CLI support package.

uv init mcp
uv add "mcp[cli]"

Prepare your API key for Nasdaq Data Link. Sign up for an API key and place it in an environment file.

cp .env.example .env

Then edit .env to include your key:

NASDAQ_DATA_LINK_API_KEY=your_api_key_here

Also set the Python path to your local clone.


4) Install the MCP server for Nasdaq Data Link with the required environment and dependencies.

uv run mcp install nasdaq_data_link_mcp_os/server.py --env-file .env --name "Nasdaq Data Link MCP Server" --with nasdaq-data-link --with pycountry


5) Verify the server connection from your MCP client (for example, Claude Desktop). The client should discover and register the Nasdaq Data Link MCP Server you installed.

## Configuration and environment notes

The server uses an environment file to supply the Nasdaq Data Link API key. You should also set the PYTHONPATH to include your local clone path so the server can import modules correctly.

Example environment variables to include in your .env file:

NASDAQ_DATA_LINK_API_KEY=your_api_key_here PYTHONPATH=/path/to/your/local/cloned/repo/nasdaq-data-link-mcp

## Development and debugging

To test and debug locally with a UI, run the MCP development flow and start the server in development mode.

mcp dev nasdaq_data_link_mcp_os/server.py --env-file .env


## Available tools

### search\_datasets

Search for datasets by keyword to discover relevant datasets such as GDP, oil prices, or mutual funds.

### get\_dataset

Fetch data from a specific dataset with optional start and end dates to obtain time series or itemized data.

### get\_dataset\_metadata

Retrieve metadata about a dataset without downloading data, such as structure and available columns.

### list\_databases

List all available Nasdaq Data Link databases accessible through the MCP server.

### export\_dataset

Export a dataset to common formats like JSON, CSV, or XML with optional date ranges.

Built by

VeilStrat

AI signals for GTM teams