Overview
Pass any city name to query a monthly updated catalog of over 150,000 settlements. The response lists matching places with their country name, two-letter ISO code, census population count, and population category. Free requests return one matching record, while paid plans include custom result limits and longitude-latitude coordinates.
Live Test City Grounding Data for AI Agents Source →
The tool
Once your client is connected to the VerveContext server, this appears in its tool list as CityGroundingDataforAIAgents. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.
{
"name": "CityGroundingDataforAIAgents",
"arguments": {
"city": "San Francisco"
}
}You do not name the tool yourself; the model picks it. Asking about San Francisco in the terms this source covers is enough for it to reach for CityGroundingDataforAIAgents on its own — naming it explicitly also works, and is the way to force the call.
Connecting
One server URL covers every source in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.
{
"mcpServers": {
"vervecontext": {
"url": "https://api.vervecontext.com/v1/mcp"
}
}
}https://api.vervecontext.com/v1/mcpPer-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.
Arguments
These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.
| Argument | Type | Description |
|---|---|---|
cityRequired | string | The city name for which you want to get the data (e.g., New York) |
limitOptionalPremium | integer | Limit number of cities that match your search criteria default 1 · range 1–20 |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"search": "San Francisco",
"foundCities": [
{
"name": "San Francisco",
"altName": "",
"country": "US",
"countryName": "United States",
"featureCode": "PPLA2",
"population": 874961,
"populationCategory": "major",
"loc": {
"type": "Point",
"coordinates": [
-122.4194,
37.7749
]
}
}
]
}
}
Response fields
Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.
| Field | Type | Example | Description |
|---|---|---|---|
search | string | San Francisco | The search query used to find cities |
foundCities | array[1] | Array of city objects matching the search criteria | |
foundCities.0.name | string | San Francisco | Official city name |
foundCities.0.altName | string | | Alternative city name or alias if available |
foundCities.0.country | string | US | Two-letter ISO country code (e.g., US) |
foundCities.0.countryName | string | United States | Full country name (e.g., United States) |
foundCities.0.featureCode | string | PPLA2 | Geonames feature code for city classification type |
foundCities.0.population | number | 874961 | City population count derived from latest census |
foundCities.0.populationCategory | string | major | City size classification based on population ranges |
foundCities.0.loc | object | {…} | |
foundCities.0.loc.type | string | Point | GeoJSON geometry type (always Point) |
foundCities.0.loc.coordinatesPremium | array | [-122.4194,37.7749] | GeoJSON coordinates as [longitude, latitude] pair |
Why ground on it
A model can produce something that looks like this answer from its training data, and be confidently out of date or simply wrong. This source returns the current value in a shape you can check, which is the difference between an answer you can cite and one you have to hedge.
Point an evaluation at search: it is the field most worth pinning a claim to, and it is either present and current or absent — never plausibly invented.
Failure modes
Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.
| Status | What it means |
|---|---|
400 / 422 | The arguments did not validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Blocked by a key restriction or an IP allow-list. Never a bad identity. |
404 | This source is not part of VerveContext. Check the catalog. |
429 | Out of credits, or a brief rate limit. The message tells them apart. |
A call costs 2 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.
Use cases
- Checkout Address Validation
- When customers enter a city name during checkout, match official country codes and alternative names to standardize shipping records.
- Retail Expansion Sizing
- Retail analysts evaluate new store candidates by querying population figures and city size categories across international regions.
- Fleet Dispatch Routing
- For regional delivery scheduling, dispatchers convert destination city names into exact longitude and latitude coordinates on paid tiers.
- Travel Destination Filtering
- To help users discover vacation spots, travel search engines group destinations by population tier and resolve local alias spellings.
Other ways to use City Grounding Data for AI Agents
Set up City Grounding Data for AI Agents on VerveContext, or reach the same source a different way. Your VerveContext account and credits work on all of them — one key, one balance.
Related
More in Geography: