mcpField
S
Statbel Be

Statbel Be

Remote
pipeworx.ioLegal & Government0Updated 5w ago

About Statbel Be

Statbel Be is an MCP server for browsing Statistics Belgium’s open-data catalogue. It helps users find saved statistical views and datasets, with multilingual dataset metadata.

Key features

  1. 01Search saved statistical views
  2. 02Retrieve view metadata by ID
  3. 03Search Statbel datasets
  4. 04Read multilingual dataset descriptions

Use cases

  1. 01Find statistical views by keyword
  2. 02Inspect the dataset linked to a view
  3. 03Look up dataset codes and language details

MCP support

It exposes Statbel view and dataset search, browsing, and metadata tools to MCP clients through Pipeworx or a local stdio server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/statbel-be/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-statbel-be

Statbel — Statistics Belgium (be.STAT / bestat) open data MCP.

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

ToolDescription
list_viewsBrowse/search Statbel (Statistics Belgium, be.STAT) saved statistical views. Each view is a pre-built table over a dataset and carries a single locale (nl/fr/de/en). Returns id, name, locale, dataSourceId and publish dates. Filter by case-insensitive substring of the view name (matches in any language).
get_viewMetadata for one Statbel view by its id (a UUID, e.g. from list_views). Returns the view object: name, locale, dataSourceId (the underlying dataset), and publish/change dates. To get the dataset description in all available languages, pass the returned dataSourceId to get_dataset.
list_datasetsBrowse/search Statbel datasets (be.STAT "datasources"). Each dataset has a name code (e.g. "IM_EAF_HOUSE_SALES_IDX"), a descriptions map with one entry per supported language (nl/fr/de/en), a category id, supportedLocales, and last-update timestamps. Filter by case-insensitive substring matched against the dataset code and all-language descriptions.
get_datasetMultilingual metadata for one Statbel dataset by its id (a UUID, e.g. the dataSourceId from a view). Returns the dataset code name, the descriptions map (nl/fr/de/en text), supportedLocales, defaultLocale, category id and update dates.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "statbel-be": {
      "url": "https://gateway.pipeworx.io/statbel-be/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/statbel-be/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/list_views \
  -H 'Content-Type: application/json' \
  -d '{"query":"house prices"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/list_views. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "statbel-be": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-statbel-be"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-statbel-be

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Statbel Be data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.