unesco-mcp

A Model Context Protocol (MCP) server for UNESCO Institute for Statistics (UIS) data. Bring the UIS Data Browser into any MCP-compatible client (Claude Desktop, Claude Code, Cursor, Windsurf, etc.).

What it does

This server connects AI assistants to the UIS API, enabling them to search indicators, retrieve data values, compare countries, and explore available breakdowns — all through natural conversation. Data is cached locally in SQLite for fast indicator discovery, while live API calls fetch the actual data values.

Available tools

Discovery

Geography

Data retrieval

Utility

Installation

PyPI (recommended)

Run the server locally from the published Python package. This requires Python 3.10+ and uv.

Claude Code:

claude mcp add unesco-mcp -- uvx unesco-mcp

Claude Desktop — add to your config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

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

Local (from source)

Use this path when developing locally or testing unreleased changes:

git clone https://github.com/lpicci96/unesco-mcp.git
cd unesco-mcp
uv sync
uv run unesco-mcp

For Claude Desktop, point the client at the checkout:

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

Claude Code:

claude mcp add unesco-mcp -- uv run --directory /path/to/unesco-mcp unesco-mcp

Example usage

Once installed, you can ask your AI assistant things like:

• "What is the primary completion rate in Kenya?"
• "Compare literacy rates across East African countries"
• "Which countries have the highest out-of-school rates?"
• "What education indicators are available broken down by sex and wealth quintile?"
• "Show me the trend in secondary enrollment for Brazil over the last 10 years"