# Nsi Bg [Health: Active]

**Category:** 🧮 Data Science Tools  
**Repository:** https://github.com/pipeworx-io/mcp-nsi-bg  
**GitHub Stars:** 0  
**npm Downloads (last month):** 460  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/nsi-bg

## Description
Bulgarian National Statistical Institute (НСИ / NSI) — Open Data API.

## Tools
Capabilities this server exposes over MCP:

- **list_datasets** — List NSI Bulgaria open-data datasets with their numeric id and English (or Bulgarian) name. Each dataset id can be passed to get_dataset for the actual figures. Use the optional `filter` to substring-match dataset names (case-insensitive), e.g. 'population', 'export', 'inflation'.
- **get_dataset** — Fetch a single NSI Bulgaria dataset by numeric id as a JSON-stat 2.0 object (dimensions, categories, and the flat `value` array). Get ids from list_datasets. Example ids: 107 (children in kindergartens by municipality), 242 (aggregate replacement ratio).
- **get_fields** — Fetch the field/dimension metadata for an NSI dataset (its column codes plus Bulgarian and English names) as parsed CSV rows. Useful for interpreting the dimension codes in a get_dataset response.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "nsi-bg": {
    "command": "npx",
    "args": ["-y","@pipeworx/mcp-nsi-bg"]
  }
}
```

## Documentation

## What Nsi Bg MCP server does

Nsi Bg MCP server exposes selected access paths to the Bulgarian National Statistical Institute’s open-data service. It is intended for agents that need to find and read official NSI datasets rather than interact with a general-purpose database.

The server has three pack-specific tools. `list_datasets` returns available datasets with numeric IDs and English or Bulgarian names. It accepts an optional case-insensitive substring filter, which helps narrow results by terms such as `population`, `export`, or `inflation`. `get_dataset` retrieves one dataset using its numeric ID. `get_fields` returns the dataset’s field and dimension metadata as parsed CSV rows, including column codes and Bulgarian and English names.

## How it works

A typical request starts with `list_datasets`. The resulting numeric ID is then supplied to `get_dataset`, which returns a JSON-stat 2.0 object. That response contains dimensions, category information, and a flat `value` array. Because the values are represented separately from the dimension metadata, use `get_fields` and the dimension details to interpret codes and map values to their meanings.

Example dataset IDs documented by the project include 107, for children in kindergartens by municipality, and 242, for aggregate replacement ratio. These examples identify available datasets but do not define the complete catalog.

The gateway endpoint also exposes shared Pipeworx meta-tools alongside the pack-specific tools. Its initialization response is the authoritative source for the tools available at a particular time. The standalone package exposes only the Nsi Bg tools and does not add the gateway’s shared routing tools.

## Setup and configuration

For an MCP client, use the streamable HTTP endpoint:

```json
{
  "mcpServers": {
    "nsi-bg": {
      "url": "https://gateway.pipeworx.io/nsi-bg/mcp"
    }
  }
}
```

The package also supports local stdio execution with no Pipeworx account or gateway round trip:

```json
{
  "mcpServers": {
    "nsi-bg": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-nsi-bg"]
    }
  }
}
```

Run `npx -y @pipeworx/mcp-nsi-bg` directly to start the local server. Clients that do not use MCP can call the gateway’s HTTP tool endpoint, such as `POST https://gateway.pipeworx.io/v1/tools/nsi_bg_list_datasets` with a JSON body containing an optional `filter`.

## Tools and capabilities

- `list_datasets`: Finds NSI datasets by name and returns their IDs.
- `get_dataset`: Retrieves one dataset as JSON-stat 2.0.
- `get_fields`: Supplies field and dimension definitions for interpreting a dataset.

Nsi Bg MCP server is useful for workflows that need official statistical figures, dataset selection by natural-language topic, or structured inspection of NSI dimensions before processing values.

## Limitations and notes

Dataset retrieval requires a numeric ID, so discovery or prior knowledge is needed before calling `get_dataset`. The returned `value` array is flat, and its interpretation depends on the accompanying dimensions, categories, and field metadata. The gateway and local modes expose different tool scopes: the gateway includes shared Pipeworx meta-tools, while the local process exposes only this pack’s three tools. The project documents MIT licensing.

_Full upstream README: https://allmcps.com/mcp/nsi-bg/readme_