OECD MCP Server

A Model Context Protocol (MCP) server providing AI assistants access to OECD's 5,000+ economic and statistical datasets via SDMX API. By connecting to the MCP server, you can use AI to search, analyze, and compare data from 38 OECD countries across economy, health, education, environment, and more.

Quick Start

The easiest way to connect an LLM / AI chatbot to the MCP server is via the published npm package oecd-mcp using npx. Below you'll find guides for different clients.

Claude Desktop

1. Open Claude Desktop settings → Developer → "Edit Config"

2. Add to the JSON file:

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

3. Save and restart Claude Desktop

Claude Code

claude mcp add oecd npx -y oecd-mcp

Verify: claude mcp list

OpenAI Codex

~/.codex/config.toml:

[mcp.oecd]
command = "npx"
args = ["-y", "oecd-mcp"]
transport = "stdio"

From Source

git clone https://github.com/isakskogstad/OECD-MCP.git
cd OECD-MCP
npm install
npm run build

Then point your client at node /absolute/path/to/OECD-MCP/dist/index.js, e.g.:

{
  "mcpServers": {
    "oecd": {
      "command": "node",
      "args": ["/absolute/path/to/OECD-MCP/dist/index.js"]
    }
  }
}

Features

The server connects to the OECD SDMX API providing access to 5,000+ datasets across 17 categories:

OECD SDMX API Access to quarterly national accounts (QNA), main economic indicators (MEI), health statistics, education data, environmental indicators, and more from 38 OECD member countries plus partner economies.

The MCP server implements the MCP protocol with support for:

• 9 tools — Dataset discovery (5) and data access (4)
• 7 resources — Categories, countries, filter guide, glossary, LLM instructions
• 7 prompt templates — Economic analysis, country comparisons, Nordic focus

Tools

| Tool | Description | | -------------

... View full README on GitHub