A community developed and maintained Model Context Protocol (MCP) server that provides access to Nasdaq Data Link. Built for use with MCP-compatible clients.

This project aims at making easy to access and explore Nasdaq Data Link’s extensive and valuable financial and economic datasets through natural language interfaces and large language models (LLMs).

🐍 This project uses the official nasdaq/data-link-python SDK

Disclaimer: This is an open-source project not affiliated with or endorsed by Nasdaq, Inc. Nasdaq® is a registered trademark of Nasdaq, Inc.

🌐 Usage

Nasdaq Data Link MCP - Retail Trading Activity	Nasdaq Data Link MCP - World Bank Data

Once installed and connected to an MCP-compatible client (e.g., Claude Desktop, this server exposes several tools that your AI assistant can use to fetch data.

In this first version (0.0.1) the project supports the following databases:

• World Bank dataset on Nasdaq Data Link (freely available for personal use);
• Nasdaq RTAT (preview available for free, full data under subscription).

Example conversations might include:

You: What were the most traded stocks by retailers yesterday?
Claude: calls get_rtat(<yetserday>) and returns relevant matches

Or:

You: What was the GDP of Italy in 2022?
Claude: Let me look that up... calls get_indicator_value tool
Claude: The GDP of Italy in 2022 was approximately ... trillion USD.

Or:

You: List all indicators related to CO₂ emissions.
Claude: calls search_worldbank_indicators("CO2") and returns relevant matches

📦 Installation

1. Clone the Repository

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

2. Install Requirements

You'll need Python 3.10+ and the mcp CLI.

pip install mcp nasdaq-data-link pycountry

MCP SDK: https://github.com/modelcontextprotocol/python-sdk
Nasdaq Data Link SDK: https://github.com/Nasdaq/data-link-python

3. Get Your API Key

Sign up on https://data.nasdaq.com/ and copy your API key.

4. Download World Bank metadata CSV (optional: only if you plan to use the World Bank database)

Download the World Bank metadata from Nasdaq Data Link:

And save it as metadata.csv in the following directory:

nasdaq-data-link-mcp/src/resources/world_data_bank/metadata/metadata.csv

5. Configure the Environment

cp .env.example .env

Then edit .env and add your API key:

NASDAQ_DATA_LINK_API_KEY=your_api_key_here

6. Start the MCP Server

mcp install src/server.py --env-file .env --name "NASDAQ Data Link MCP Server"

This registers the server with your MCP client (e.g., Claude Desktop).

🛠️ Tools

After installation, the following tools are exposed to MCP clients:

{
  "action": "tool",
  "name": "get_rtat10",
  "params": {
    "dates": "2025-03-31,2025-03-28,2025-03-27",
    "tickers": "TSLA,TQQQ,SQQQ"
  }
}

{
  "action": "tool",
  "name": "get_rtat",
  "params": {
    "dates": "2025-03-31,2025-03-28,2025-03-27",
    "tickers": "TSLA,TQQQ,SQQQ"
  }
}

{
  "action": "tool",
  "name": "get_indicator_value",
  "params": {
    "country": "Italy",
    "indicator": "NY.GDP.MKTP.CD"
  }
}

{
  "action": "tool",
  "name": "country_code",
  "params": {
    "countryName": "Italy"
  }
}

{
  "action": "tool",
  "name": "list_worldbank_indicators"
}

{
  "action": "tool",
  "name": "search_worldbank_indicators",
  "params": {
    "keyword": "population"
  }
}

🧪 MCP Dev & Debugging

To test the server locally with a UI:

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

This opens the MCP Dev interface where you can call tools manually, inspect results, and troubleshoot.

📊 Architecture Diagram

graph TD
  subgraph "Local Machine"
    A[MCP Server: Nasdaq Data Link MCP] --> C[MCP Client, ie. Claude Desktop]
  end

  C -->|user prompt| D[LLM ie. Claude 3.7 Sonnet]
  D -->|calls tool| A
  A -->|fetches data| B[Nasdaq Data Link API]
  B -.-> E[Retail Trading Activity Tracker]
  B -.-> F[World Bank Metadata]

📚 References

• Model Context Protocol Python SDK
• Nasdaq Data Link Python SDK

📄 License

MIT License © 2025 Stefano Amorelli