Nearest feature and its distance

For each feature of a layer, the nearest feature of a second layer and the distance to it.

Request

curl -X POST https://mcp.terra-lab.ai/v1/tools/find_nearest_features \
  -H "Authorization: Bearer $TERRALAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://mcp.terra-lab.ai/dl/geojson/TOKEN/buildings.geojson","with_url":"https://mcp.terra-lab.ai/dl/geojson/TOKEN/pois.geojson","join_fields":["name"]}'

import os
import requests

response = requests.post(
    "https://mcp.terra-lab.ai/v1/tools/find_nearest_features",
    headers={"Authorization": f"Bearer {os.environ['TERRALAB_API_KEY']}"},
    json={
        "url": "https://mcp.terra-lab.ai/dl/geojson/TOKEN/buildings.geojson",
        "with_url": "https://mcp.terra-lab.ai/dl/geojson/TOKEN/pois.geojson",
        "join_fields": ["name"],
    },
    timeout=120,
)
response.raise_for_status()
print(response.json()["structuredContent"])

const response = await fetch('https://mcp.terra-lab.ai/v1/tools/find_nearest_features', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.TERRALAB_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "url": "https://mcp.terra-lab.ai/dl/geojson/TOKEN/buildings.geojson",
    "with_url": "https://mcp.terra-lab.ai/dl/geojson/TOKEN/pois.geojson",
    "join_fields": [
      "name"
    ]
  }),
});
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, for each feature of a layer, the nearest feature of a second layer and the distance to it: the closest school to each building, the nearest road to each point. Both layers can be an uploaded file, a link, inline GeoJSON or a TerraLab download link, up to 20,000 features each. Adds nearest_distance_m (geodesic on the WGS 84 ellipsoid, between the two closest points, 0 when they touch) and the chosen fields of the nearest feature as nearest_. Returns the least, median and greatest distance, sample rows, a map and GeoJSON, KML, Shapefile zip, GeoPackage and CSV downloads. Not a road distance or travel time (get_travel_times). Never use the user's current location unless they type it. Download links build their file when opened; no file is saved. The user opens the file in QGIS or any GIS: this server cannot load it into the user's own QGIS or any app on their computer. Never pass these links to open_gis_file: list every format the user needs in formats, in this one call. TerraLab reads the file or link to answer and keeps no copy.