World Bank Data

You run a World Bank Data360 MCP Server that exposes the World Bank Data360 OPEN API to Claude Desktop, enabling you to search and retrieve historical economic and social indicators across many countries with simple natural language prompts.

How to use

Ask Claude questions like “Get world poverty data for 2024” or “Show me GDP per capita for Japan in 2020.” Claude will search for datasets, check available years, apply filters (country, year, demographics), and present the results in a clear, formatted way.

You have access to tools that support searching datasets, querying available temporal coverage, and retrieving data with filters. Use these patterns to assemble your analytics workflows without leaving Claude.

How to install

Prerequisites you should have on your machine before starting: Python is installed, and you can run the uv tool used to start and manage the MCP server.

Step 1: Open a terminal and navigate to your project directory.

cd /Users/llnormll/WorkSpace/world-bank-mcp

Step 2: Install dependencies and prepare the environment by syncing with the MCP runtime.

uv sync

Step 3: Start the MCP server to test locally.

uv run world_bank_mcp/server.py

Claude Desktop configuration

{
  "mcpServers": {
    "world-bank-data": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/world-bank-mcp",
        "run",
        "src/world_bank_mcp/server.py"
      ]
    }
  }
}

Notes

Restart Claude Desktop after adding or updating the MCP configuration to ensure it picks up the new server setup.

Data sources

WB_WDI: World Development Indicators; WB_HNP: Health, Nutrition & Population Statistics; WB_GDF: Global Development Finance; WB_IDS: International Debt Statistics.

Common country codes

USA, CHN, JPN, DEU, GBR, FRA, IND, BRA, RUS, CAN, KOR, AUS, MEX, IDN, TUR, SAU, ARG, ZAF, ITA, ESP.

License

MIT.

Available tools

search_datasets

Search for datasets by keywords. Use optimized queries like "gross domestic product total" to find relevant indicators.

get_temporal_coverage

Retrieve available years for a specific dataset.

retrieve_data

Fetch actual data with filters such as year, countries, and demographics.