# Data Lv [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://github.com/pipeworx-io/mcp-data-lv  
**GitHub Stars:** 0  
**npm Downloads (last month):** 1013  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/data-lv

## Description
Latvia Open Data (data.gov.lv) CKAN MCP.

## Tools
Capabilities this server exposes over MCP:

- **search_datasets** — Search Latvia Open Data (Latvia) for datasets by keyword. Returns each dataset's id/name, title, organization, and its resources (each with a resource_id for query_resource).
- **dataset** — Show full metadata for one Latvia Open Data dataset by id or name (from search_datasets), including all resources and their resource_ids.
- **query_resource** — Pull rows from a tabular Latvia Open Data resource (CKAN DataStore) by resource_id (from a dataset's resources). Optional full-text q, limit, offset. Note: only resources with the DataStore enabled are queryable.

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

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

## Documentation

## What Data Lv does

Data Lv exposes Latvia’s public CKAN catalog at data.gov.lv as MCP tools. It is useful for agents that need to locate Latvian datasets, identify the organization responsible for a dataset, inspect available resources, or retrieve records from resources backed by CKAN DataStore.

The integration is independent and unofficial. It operates through Pipeworx rather than being published or endorsed by the Latvian open-data provider.

## How it works

The hosted MCP endpoint is available at `https://gateway.pipeworx.io/data-lv/mcp`. An MCP client connects to that URL and can call the pack’s three catalog tools. The endpoint also exposes shared Pipeworx meta-tools, including routing and discovery functions, so the tool list is larger than the three Data Lv-specific tools. The connection’s initialization response defines the exact scope available at connection time.

A full Pipeworx gateway endpoint is also available at `https://gateway.pipeworx.io/mcp`. Both gateway URLs provide access to the same broader collection of data sources; the difference is which pack’s tools appear directly in the listing.

For clients without MCP support, Pipeworx provides HTTP tool endpoints. For example, dataset search can be invoked with a POST request to `/v1/tools/data_lv_search_datasets` and a JSON query such as `{"query":"population"}`.

## Setup and configuration

Add the hosted endpoint to an MCP client such as Claude Desktop, Cursor, or Windsurf:

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

The npm package `@pipeworx/mcp-data-lv` provides a local stdio bridge. Configure the client to run it with `npx`:

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

The bridge requires network access and does not provide offline operation. Anonymous use is limited to 50 calls per day. A free Pipeworx account increases the allowance to 200 calls per day; pass the account key as `PIPEWORX_API_KEY` in the client’s environment. Set `PIPEWORX_META_TOOLS=1` when the local bridge should also list the shared gateway tools.

## Tools and capabilities

- `search_datasets` finds Latvia Open Data datasets by keyword and returns identifiers, names, titles, organizations, and resource details.
- `dataset` retrieves complete metadata for a dataset selected by its ID or name, including its resources and resource IDs.
- `query_resource` reads rows from a tabular CKAN DataStore resource. It accepts a resource ID and can apply full-text search with `q`, plus `limit` and `offset` for result control.

Resource IDs come from dataset search or metadata results. Only resources with CKAN DataStore enabled can be queried for rows.

## Limitations and notes

The MCP-specific tools focus on catalog discovery, metadata, and DataStore-backed tabular data. A resource that lacks DataStore support cannot be queried with `query_resource`. The hosted and npm configurations route requests through Pipeworx, so network connectivity is required. Calls made with an API key use Bearer authentication and are metered according to Pipeworx account terms.

_Full upstream README: https://allmcps.com/mcp/data-lv/readme_