Imf Data MCP

🚀 IMF Data MCP Server

This MCP server integrates with the free IMF Data API, offering a range of tools and resources for retrieving and processing economic data. It enables users to query datasets, obtain time - series data, and list available indicators and countries, facilitating more convenient use of IMF data in a structured and programmable manner.

🚀 Quick Start

The IMF Data MCP Server provides seamless integration with the IMF Data API, allowing users to efficiently access and manage economic data.

✨ Features

• List Datasets: Retrieve all available IMF datasets via the Dataflow API.
• Get Dataset Structure: Obtain the structure of a specified dataset through the DataStructure API.
• Retrieve Time - Series Data: Use the CompactData API to retrieve time - series data for various datasets (e.g., CDIS, CPIS, MFS, IFS, etc.).
• List Indicators: List all available indicators for a specific dataset via the DataMapper API.
• List Countries: Retrieve the list of available countries for a specific dataset.
• Query Prompt Template: Provide a query prompt template to guide users on how to query data using indicators and intentions.

📦 Installation

Using uv (Recommended)

You can directly run the server using uvx without additional installation:

uvx imf-data-mcp

Using PIP

Alternatively, you can install the server using pip:

pip install imf-data-mcp

After installation, run the server:

python -m imf_data_mcp

📚 Documentation

Configuration

The server can be configured according to different application scenarios. For example, to integrate with a specific application, you can add the following configuration:

{
  "mcpServers": {
    "imf": {
      "command": "uvx",
      "args": ["imf-data-mcp"]
    }
  }
}

Debugging

To debug the server, you can use the MCP inspector. For installations using uvx, run:

npx @modelcontextprotocol/inspector uvx imf-data-mcp

🔧 Contribution Guidelines

We welcome contributions to the imf - data - mcp project. Whether it's adding new tools, enhancing existing features, or improving documentation, your input is highly valuable. Please feel free to submit pull requests or open issues.

📄 License

This project is licensed under the Apache 2.0 license. For more details, please refer to the LICENSE file.