The Financial Datasets MCP Server exposes tools that let you retrieve company financials, stock prices, and market news directly through MCP as a voice or chat assistant. Available tools include: get_income_statements, get_balance_sheets, get_cash_flow_statements, get_current_stock_price, get_historical_stock_prices, get_company_news, get_available_crypto_tickers, get_crypto_prices, get_historical_crypto_prices, and get_current_crypto_price. Each tool accepts a company or crypto identifier and optional date ranges or data parameters, returning structured financial data and market information that you can feed into your AI prompts or UI workflows. The server is designed to plug into Claude Desktop or other MCP-compatible clients via an MCP server entry named financial-datasets, enabling you to query financial data as part of your conversational experience.

To use the tools, you first start the server (see installation). Once running, connect your MCP client (e.g., Claude Desktop) to the financial-datasets MCP server. In Claude Desktop, you will see a suite of tools under the financial-datasets entry, such as requesting Apple's income statements or querying the current price of Tesla stock. You can then compose natural language questions like, “Show me Microsoft's income statements for the last quarter” or “What was the current price of AAPL?” and the MCP client will route them through the server to fetch and return the data.

Prerequisites:

• Python 3.10 or higher
• Access to a Python environment (virtualenv or venv)
• Git

Installation steps:

1. Clone the repository: git clone https://github.com/financial-datasets/mcp-server cd mcp-server

2. Set up a Python virtual environment and activate it: python -m venv .venv

   macOS/Linux

   source .venv/bin/activate

   Windows

   .venv\Scripts\activate

3. Install dependencies (adjust if you have a requirements.txt or setup.py in the project): pip install -r requirements.txt # if a requirements file exists

   Or install package dependencies as needed, e.g., pip install mcp[cli] httpx if required by your project setup

4. Configure environment variables:

   Create a .env file or export in your shell

   FINANCIAL_DATASETS_API_KEY=your-financial-datasets-api-key

5. Run the server: python server.py

6. Verify the server starts and is listening for MCP requests. Once running, you can connect your MCP client to the server using the server name financial-datasets.

Notes and tips:

• Ensure FINANCIAL_DATASETS_API_KEY is set correctly; the server will fail to retrieve data without a valid key.
• If you encounter import or dependency issues, install via a clean virtual environment and install dependencies according to the project’s setup instructions.
• When integrating with Claude Desktop or other MCP clients, point the client to the financial-datasets MCP server and use the documented tool names exactly (e.g., get_income_statements, get_current_stock_price).
• For historical data queries, provide clear date ranges to avoid large responses or API limits.
• If you need crypto data, the server exposes get_available_crypto_tickers, get_crypto_prices, get_historical_crypto_prices, and get_current_crypto_price for cryptocurrency markets in addition to traditional equities.