mcp-cbs-cijfers-open-data
MCP server for working with CBS Cijfers Open Data
dstotijn
README
mcp-cbs-cijfers-open-data
This project provides a Model Context Protocol (MCP) server for the CBS Open Data API. It allows AI tools to interact with the CBS Open Data through MCP tools.
Features
- Implements a Model Context Protocol (MCP) server
- Provides tools for interacting with the CBS Open Data:
- List available datasets and catalogs
- Query dataset metadata and dimensions
- Retrieve statistical data with filtering options
- Explore dimension values
Tools
This MCP server provides the following tools for AI assistants to interact with the CBS Open Data API:
get_catalogs
Retrieves all available CBS data catalogs.
Parameters:
- None
query_datasets
Lists available datasets from the CBS Open Data API with advanced filtering, sorting, and pagination options.
Parameters:
catalog
(required): Catalog identifier (use "CBS")select
(optional): OData $select parameter to choose specific fieldsfilter
(optional): OData $filter parameter for filtering resultsorderby
(optional): OData $orderby parameter for sorting resultstop
(optional): OData $top parameter for limiting resultsskip
(optional): OData $skip parameter for paginationcount
(optional): OData $count parameter to include count in responsesearch
(optional): OData $search parameter for free-text searchexpand
(optional): OData $expand parameter to include related entities
get_dimensions
Retrieves all dimensions for a specific dataset.
Parameters:
catalog
(required): Catalog identifierdataset
(required): Dataset identifier
get_dimension_values
Retrieves all values for a specific dimension with filtering and sorting options.
Parameters:
catalog
(required): Catalog identifierdataset
(required): Dataset identifierdimension
(required): Dimension identifierselect
(optional): OData $select parameter to choose specific fieldsfilter
(optional): Additional OData $filter parameter for filtering resultsorderby
(optional): OData $orderby parameter for sorting resultstop
(optional): OData $top parameter for limiting results
get_observations
Retrieves observations from a specific dataset with optional filters.
Parameters:
catalog
(required): Catalog identifierdataset
(required): Dataset identifierfilters
(optional): Filters as key-value pairslimit
(optional): Maximum number of observations to return
query_observations
Queries observations with advanced OData query options to filter, sort, and shape results.
Parameters:
catalog
(required): Catalog identifierdataset
(required): Dataset identifierselect
(optional): OData $select parameter to choose specific fieldsfilter
(optional): OData $filter parameter for filtering resultsorderby
(optional): OData $orderby parameter for sorting resultstop
(optional): OData $top parameter for limiting resultsskip
(optional): OData $skip parameter for paginationcount
(optional): OData $count parameter to include count in responsesearch
(optional): OData $search parameter for free-text searchexpand
(optional): OData $expand parameter to include related entities
get_metadata
Retrieves the OData service metadata document for the CBS API.
Parameters:
- None
Requirements
Installation
Configuration for common MCP hosts (Claude Desktop, Cursor):
{
"mcpServers": {
"cbs-cijfers-open-data": {
"command": "go",
"args": ["run", "github.com/dstotijn/mcp-cbs-cijfers-open-data@latest"]
}
}
}
Alternatively, you can manually install the program (given you have Go installed ):
go install github.com/dstotijn/mcp-cbs-cijfers-open-data@latest
Usage
$ mcp-cbs-cijfers-open-data --help
Usage of mcp-cbs-cijfers-open-data:
-http string
HTTP listen address for JSON-RPC over HTTP (default ":8080")
-sse
Enable SSE transport
-stdio
Enable stdio transport (default true)
Typically, your MCP host will run the program and start the MCP server, and you don't need to manually do this. But if you want to run the MCP server manually, for instance because you want to serve over HTTP (using SSE):
Given you have your PATH
environment configured to include the path named by
$GOBIN
(or $GOPATH/bin
$HOME/go/bin
if $GOBIN
is not set), you can then
run:
mcp-cbs-cijfers-open-data --stdio=false --sse
Which will output startup logs with the SSE transport URL:
CBS API MCP server started, using transports: [sse]
SSE transport endpoint: http://localhost:8080
© 2025 David Stotijn — This project is licensed under the Apache License 2.0
Recommended Servers
Crypto Price & Market Analysis MCP Server
A Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.
MCP PubMed Search
Server to search PubMed (PubMed is a free, online database that allows users to search for biomedical and life sciences literature). I have created on a day MCP came out but was on vacation, I saw someone post similar server in your DB, but figured to post mine.
dbt Semantic Layer MCP Server
A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.
mixpanel
Connect to your Mixpanel data. Query events, retention, and funnel data from Mixpanel analytics.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Nefino MCP Server
Provides large language models with access to news and information about renewable energy projects in Germany, allowing filtering by location, topic (solar, wind, hydrogen), and date range.
Vectorize
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Mathematica Documentation MCP server
A server that provides access to Mathematica documentation through FastMCP, enabling users to retrieve function documentation and list package symbols from Wolfram Mathematica.
kb-mcp-server
An MCP server aimed to be portable, local, easy and convenient to support semantic/graph based retrieval of txtai "all in one" embeddings database. Any txtai embeddings db in tar.gz form can be loaded
Research MCP Server
The server functions as an MCP server to interact with Notion for retrieving and creating survey data, integrating with the Claude Desktop Client for conducting and reviewing surveys.