Stat Gl logo

Stat Gl

Queries Statistics Greenland PxWeb data by browsing subjects, reading table metadata, and requesting filtered observations.

Install Stat Gl

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "stat-gl": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-stat-gl"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @pipeworx/mcp-stat-gl

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 9d ago.

Overview

Stat Gl MCP server exposes Statistics Greenland’s PxWeb database through tools for browsing subjects, inspecting table metadata, and querying observations. It works through a hosted MCP endpoint or as a local stdio package installed with npx. Use it when an agent needs structured Greenland statistics and must discover valid dimensions and codes before querying a table.

Use cases

  • Browse Greenland statistical subjects
  • Inspect PxWeb table dimensions
  • Build filtered PxWeb queries
  • Retrieve observations as json-stat2

Key features

  • Subject-tree browsing
  • Table metadata lookup
  • Dimension code discovery
  • Filtered PxWeb queries
  • json-stat2 responses
  • Hosted and local MCP access

Tools3

What Stat Gl lets your agent do. Expand a tool for its parameters.

Self-reported~226 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

8/8 checks healthy over the last 50d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · @pipeworx/mcp-stat-gl (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads443Package downloads in the last 30 days.
Last commit1mo agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed3Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Stat Gl works

What Stat Gl MCP server does

The Stat Gl MCP server connects AI agents to the Statistics Greenland (Grønlands Statistik) PxWeb database. It provides a focused set of tools for finding statistical tables, understanding their dimensions, and retrieving observations in json-stat2 format.

The service is useful when a question depends on official Greenland statistics organized in PxWeb. An agent can start at the database root, locate a subject or table, inspect the table’s available dimensions and coded values, then submit a query using those codes. This workflow avoids guessing table paths or selection values.

How it works

The Stat Gl MCP server can be reached through the hosted MCP URL https://gateway.pipeworx.io/stat-gl/mcp. The same gateway also exposes shared Pipeworx meta-tools, including routing and discovery tools, so the hosted endpoint may list more tools than the three Stat Gl data tools. Its initialize response defines the exact scope returned for a connection.

A local alternative runs the package as an MCP server over standard input and output. The local mode exposes only the Stat Gl pack’s tools and does not add the gateway’s shared meta-tools. The gateway and local package use the same underlying tool set.

The main sequence is:

  1. Call subjects with an empty path to see root folders and tables.
  2. Provide a path such as BE/BE01 to browse deeper.
  3. Pass a complete table path ending in .px or .PX to table_meta.
  4. Use the returned dimension codes and values to construct a query_table request.
  5. Read the returned observations as json-stat2.

Setup and configuration

For an MCP client, add the hosted endpoint as a server URL:

config.json
{
  "mcpServers": {
    "stat-gl": {
      "url": "https://gateway.pipeworx.io/stat-gl/mcp"
    }
  }
}

The README names Claude Desktop, Cursor, and Windsurf as compatible clients. The local package can be started with npx -y @pipeworx/mcp-stat-gl, or configured with a command and the same package argument. This local mode does not require a Pipeworx account or a gateway round trip.

The tools can additionally be called over HTTP. For example, the hosted tool endpoint accepts a POST request at /v1/tools/stat_gl_subjects with a JSON body containing a path value.

Tools and capabilities

The Stat Gl MCP server includes these data tools:

  • subjects browses the /Greenland subject tree. An empty path returns root folders and tables; a sub-path narrows the listing.
  • table_meta returns a table’s dimensions, valid codes, and value lists. The path must include the complete table identifier and its .px or .PX suffix.
  • query_table submits a PxWeb query and returns json-stat2 observations. Its body uses query entries containing a dimension code and a selection with filter and values, plus a response format of json-stat2.

An empty query requests the full table, but large tables may reject that request. Narrow selections are therefore preferable, using codes obtained from table_meta.

Limitations and notes

The service is specific to Statistics Greenland’s PxWeb data and does not describe arbitrary databases. Table paths and dimension codes must match the source metadata. Results use json-stat2 rather than a separately documented tabular format. The hosted endpoint includes shared gateway tools, while the standalone stdio process does not. No environment variables are documented for running the server.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Stat Gl

Stat Gl is an MCP server that connects AI agents to Statistics Greenland’s PxWeb database. Its main tools browse the subject tree, fetch table metadata with valid dimension codes and values, and submit filtered table queries that return observations in json-stat2 format.

Install it locally with `npx -y @pipeworx/mcp-stat-gl` and configure that command in an MCP client. You can instead connect to `https://gateway.pipeworx.io/stat-gl/mcp` without installing the package.

Yes, Stat Gl works with Cursor through the hosted MCP URL. Add `https://gateway.pipeworx.io/stat-gl/mcp` as the server URL in the client configuration.

First browse with `subjects`, then call `table_meta` with the full table path to obtain valid dimension codes and values. Submit those selections to `query_table` using the required PxWeb body and request `json-stat2` output.

Yes, you can run the package locally over stdio without a Pipeworx account.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewStat Gl AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/stat-gl?style=directory)](https://allmcps.com/mcp/stat-gl)
HTML Embed
<a href="https://allmcps.com/mcp/stat-gl"><img src="https://allmcps.com/api/badge/stat-gl?style=directory" alt="Stat Gl on AllMCPs" /></a>