FRED Economic Data MCP server for AI agents

This MCP server implementation provides tools to search and retrieve economic data series from the Federal Reserve Economic Data (FRED) API. It allows you to easily access economic data through a Model Context Protocol interface.

Prerequisites

Node.js (v16 or higher)
FRED API Key (obtain from FRED API)

Installation

Clone the repository:

git clone https://github.com/kablewy/fred-mcp-server
cd fred-mcp-server

Install dependencies:
```
npm install
```

Set up environment variables:

# Copy the example environment file
cp .env.example .env

# Edit the .env file and add your FRED API key
FRED_API_KEY=your_api_key_here

Running the Server

Development Mode

To run the server during development with automatic reloading:

npm run dev

Production Mode

For production deployment:

Build the project first:
```
npm run build
```
Start the production server:
```
npm start
```

Available Tools

The FRED MCP server provides access to the following tools:

Series Search

Use this tool to search for economic data series using various parameters. This allows you to find relevant economic indicators and datasets.

Series Observations

Retrieve actual data observations for specific economic series. This tool supports:

Date range filtering - Get data within specific time periods
Frequency adjustment - Convert between different time frequencies
Aggregation methods - Apply different aggregation techniques to the data
Sorting and pagination - Control how results are organized and limited

Example Usage

Once the server is running, you can connect to it using any MCP client. The server exposes endpoints for searching economic data series and retrieving observations based on your specified parameters.

For specific API usage examples, refer to the MCP client documentation for how to connect to this server and utilize the available tools.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.