5 tools for discovering and querying Eurostat statistical datasets:

Search the Eurostat dataset catalogue by keyword.

• Case-insensitive substring match against dataset labels across 8,933 datasets
• Returns code, label, type (dataset/table), period coverage, observation count, and theme breadcrumb
• Configurable result limit (1–100, default 20); reports total matches before the limit
• Catalogue loaded once per session from the Eurostat TOC file
• Pair with eurostat_browse_themes for structured domain exploration when keywords are unclear

Navigate the Eurostat theme tree.

• Without theme_code: returns the 11 top-level themes (Economy and finance, Population, Transport, etc.)
• With theme_code: returns immediate children — subtheme folders and datasets in that branch
• Each entry includes code, label, type (folder/dataset/table), data period, and observation count where available
• Returns a breadcrumb path from root to the current node
• Use for structured discovery when you know the domain but not the exact dataset code

Fetch metadata for a Eurostat dataset before querying it.

• Returns all dimensions with their codes, labels, and up to 10 sample values each
• Reports overall time range and total observation count across all periods
• Uses a minimal Statistics API call (most recent period only) for efficiency
• For dimensions with more than 10 values, use eurostat_get_dimension_values for the full list
• Provides a link to the ESMS metadata page when available

List all valid values for a specific dataset dimension.

• Retrieves the complete set of valid codes and labels for any dimension (unit, na_item, geo, etc.)
• For the geo dimension, supports NUTS hierarchy filtering: aggregate (EU/EA totals), country (41 states), nuts1 (127 major regions), nuts2 (309 basic regions), nuts3 (1,343 small regions)
• Prevents silent no-data returns — invalid dimension values in eurostat_query_dataset return nothing without error; verify codes here first

Fetch statistical data from a Eurostat dataset.

• Accepts dimension filters as a map of {dimension_code: [value1, value2, ...]}
• NUTS geo-level filter (aggregate, country, nuts1, nuts2, nuts3) — mutually exclusive with a geo key in filters
• Time range via since_period/until_period (e.g., "2020", "2023-Q1") or last_n_periods for the N most recent
• Returns decoded observations with dimension codes and labels, numeric values, and status flags (p = provisional, e = estimated, etc.)
• Reports total observation count, missing value count, and effective time range of the result
• Async-response detection — large unfiltered queries return an actionable error with filter guidance rather than silently timing out

Built on @cyanheads/mcp-ts-core:

• Declarative tool definitions — single file per tool, framework handles registration and validation
• Unified error handling across all tools
• Pluggable auth (none, jwt, oauth)
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• Runs locally (stdio/HTTP) or on Cloudflare Workers from the same codebase

Eurostat-specific:

• Session-level in-memory cache for the TOC file — loaded once, reused across all search and browse calls
• JSON-stat 2.0 stride-based decoder for the Statistics API response format
• Async-response detection — Eurostat returns a warning object rather than an error for over-limit queries; the server intercepts it and returns an actionable error with filter guidance
• NUTS hierarchy geo-level filtering across query and dimension-value tools
• Status flag decoding (provisional, estimated, definition differs, etc.)

Agent-friendly output:

• Discovery workflow: eurostat_search_datasets / eurostat_browse_themes → eurostat_get_dataset_info → eurostat_get_dimension_values → eurostat_query_dataset
• Invalid dimension codes in query filters silently return no data from Eurostat — the eurostat_get_dimension_values tool prevents this by letting agents verify codes first
• Structured error contracts with typed reasons and recovery hints on all tools

A public instance is available at https://eurostat.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "eurostat-mcp-server": {
      "type": "streamable-http",
      "url": "https://eurostat.caseyjhand.com/mcp"
    }
  }
}

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "eurostat-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/eurostat-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "eurostat-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/eurostat-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "eurostat-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/eurostat-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

• Bun v1.3.2 or higher. No API key required — Eurostat's dissemination API is public.

1. Clone the repository:

git clone https://github.com/cyanheads/eurostat-mcp-server.git

2. Navigate into the directory:

cd eurostat-mcp-server

3. Install dependencies:

bun install

All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Key environment variables:

• Build and run the production version:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:http
  # or
  bun run start:stdio

• Run checks and tests:

  bun run devcheck  # Lints, formats, type-checks, and more
  bun run test      # Runs the test suite

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for logging, ctx.state for storage
• Register new tools and resources in the createApp() arrays

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.