home / mcp / world bank mcp server

World Bank MCP Server

An implementation of the Model Context Protocol for the World Bank open data API

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "anshumax-world_bank_mcp_server": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/world_bank_mcp_server",
        "run",
        "world_bank_mcp_server"
      ]
    }
  }
}

You can interact with the World Bank open data API through a dedicated MCP server that lets you list countries and indicators and analyze indicators for multiple nations. This server provides structured endpoints for querying World Bank data and includes comprehensive logging to help you monitor its activity.

How to use

Connect to the World Bank MCP Server from your MCP client to list available countries and indicators or to perform indicator analyses. Use the server to fetch data, run analyses like population segments or poverty indicators, and review the results within your AI assistant workflows. The server is designed to be run locally and then queried by your client using its MCP interface.

How to install

Prerequisites you should have before starting: Node.js and npm are commonly used in MCP workflows, and you will need the MCP runtime utilities available on your system. The following steps show how to install and run the World Bank MCP Server for Claude Desktop workflows.

# Step 1: Install the World Bank MCP Server for Claude Desktop
npx -y @smithery/cli install @anshumax/world_bank_mcp_server --client claude

# Step 2: Prepare Claude Desktop configuration
# Add the MCP server configuration to your Claude Desktop config

Additional notes

The World Bank MCP Server exposes a local runtime via a standard runtime command. You only need to run the provided runtime command within your environment to start the server, and then you can connect your MCP client to it. If you are using Claude Desktop, configure it to point to the server using the specified runtime command.

Configuration and usage details

The World Bank MCP Server supports a local runtime execution model. You start the server by invoking the runtime with the appropriate directory and server name. When your client requests data, the server responds with lists of countries, indicators, and analysis results for selected nations.

Troubleshooting and tips

If you encounter issues starting the server, verify the runtime command and directory path you provided in your client configuration. Check the server logs for any errors or warnings that indicate missing data sources or connectivity problems with the World Bank API. Ensure that your client is correctly configured to connect to the local runtime endpoint.

Available tools

list_countries

Lists all countries available in the World Bank open data API so you can choose targets for analysis.

list_indicators

Retrieves all indicators available from the World Bank open data API to help you focus on relevant metrics.

analyse_indicators

Performs analysis on selected indicators for specified countries, such as population, poverty, and other demographic metrics.

logging

Provides comprehensive logging to help you monitor requests and server activity for auditing and debugging.