Describe a cloud GeoParquet dataset

What a public cloud GeoParquet holds, read from its footer only: rows, columns with their ranges, geometry, CRS, extent and partitions.

Request

curl -X POST https://mcp.terra-lab.ai/v1/tools/inspect_dataset \
  -H "Authorization: Bearer $TERRALAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"dataset":"portolan:nasa-firms-active-fire/detections"}'

import os
import requests

response = requests.post(
    "https://mcp.terra-lab.ai/v1/tools/inspect_dataset",
    headers={"Authorization": f"Bearer {os.environ['TERRALAB_API_KEY']}"},
    json={
        "dataset": "portolan:nasa-firms-active-fire/detections",
    },
    timeout=120,
)
response.raise_for_status()
print(response.json()["structuredContent"])

const response = await fetch('https://mcp.terra-lab.ai/v1/tools/inspect_dataset', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.TERRALAB_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "dataset": "portolan:nasa-firms-active-fire/detections"
  }),
});
const data = await response.json();
console.log(data.structuredContent);

Parameters

A JSON object in the request body; in an MCP client, the arguments of the tool call.

Response

structuredContent holds the result, content the same result as text for a model, and isError is true when the tool refused the request or failed; then structuredContent.code, message and hint say what to change.

{
  "structuredContent": {
    "sources": [{ "name": "...", "licence": "...", "url": "..." }],
    "downloads": [{ "label": "...", "format": "...", "url": "...", "name": "..." }]
  },
  "content": [{ "type": "text", "text": "..." }],
  "isError": false
}

Every result lists its sources with their licence. File results come as downloads: each link builds its file when opened.

Errors

A missing key answers 401, an empty balance 402, too many calls 429. A call that fails or finds nothing is not counted. See Errors and rate limits.

Description for agents

The text the server gives an agent to decide when to call this tool:

Use this when the user wants to know what a public cloud GeoParquet holds before querying it: "what columns does the Fields of The World file have?", "which years does the FIRMS fire archive cover?". Give dataset: a portolan: id from find_datasets (open_registry), or the https URL of a GeoParquet file or of a hive-partitioned folder (.../year=*/x.parquet). Reads only the file footer, never the rows: row count, row groups, columns with type, min, max and null count, geometry column, CRS and bbox, compression, and for a partitioned dataset its partitions (keys and values). zone_queries says whether aggregate_dataset can count it per zone. Then aggregate_dataset counts or sums it per zone and extract_dataset cuts it to an area.