# Local Business Finder — OpenStreetMap POIs, No Key (`noniner/osm-local-business-finder`) Actor

Find local businesses by area and category straight from OpenStreetMap: name, category, address, phone, website and coordinates — no API key, no Maps bill. A free building block for local lead lists and market mapping. Optional AI tagging.

- **URL**: https://apify.com/noniner/osm-local-business-finder.md
- **Developed by:** [Fredrik Hansson](https://apify.com/noniner) (community)
- **Categories:** Lead generation, AI, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$200.00 / 1,000 area searcheds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Local Business Finder — OpenStreetMap POIs, No Key

**A free, keyless building block for local lead lists — no Google Maps bill.** Give it an area ("Shoreditch, London", "Austin, Texas") and a few categories ("restaurant", "cafe", "dentist", "gym"), and it returns every matching local business straight from **OpenStreetMap**: name, category, address, phone, website and coordinates. No API key. No Maps quota. No per-place Google charge.

You bring a place and a category. It hands back a clean, structured list.

***

### The flow

```
   area + categories            Nominatim geocode            Overpass POI query           structured list
  "Shoreditch, London"   →    area → bounding box     →    all POIs in the box     →    name · category · addr
  ["cafe","restaurant"]        (free OSM geocoder)          for every category           phone · website · lat/lon
```

1. **Geocode the area** — the place name goes to OpenStreetMap's **Nominatim** geocoder, which returns a bounding box.
2. **Map categories to OSM tags** — "restaurant" → `amenity=restaurant`, "gym" → `leisure=fitness_centre`, "bakery" → `shop=bakery`, and so on (~15 common categories; unknown ones fall back to a name search).
3. **Query Overpass** — one [Overpass API](https://overpass-api.de/) call pulls every matching node/way inside the box.
4. **Parse + dedupe** — one clean record per named business, capped to `maxResults`.

***

### What you get per business

For every named business in the area, the Actor returns:

1. **`name`** — the business name as mapped in OpenStreetMap.
2. **`category`** — which of your input categories matched.
3. **`address`, `city`, `postcode`** — assembled from OSM address tags where present.
4. **`phone`** — from `phone` / `contact:phone`.
5. **`website`** — from `website` / `contact:website`.
6. **`openingHours`** — the raw OSM opening-hours string, when available.
7. **`lat`, `lon`** — coordinates (the node point, or the way's center).
8. **`osmType`, `osmId`, `osmUrl`** — a direct link back to the element on openstreetmap.org.
9. **`categoryNote`** *(optional)* — a one-line AI positioning note, only when AI tagging is on.

> **Note on completeness:** OpenStreetMap is crowd-sourced, so coverage and the richness of each tag (phone, website, hours) **vary by area**. Dense, well-mapped neighbourhoods return a lot; sparse rural areas return less.

***

### Three ways people use it

- **Local lead lists** — build a free, keyless list of businesses by category and neighbourhood for cold outreach, then enrich further (emails, website signals) with downstream Actors. **local lead generation** without a Google Maps bill.
- **Market / territory mapping** — count and map the cafes, gyms, dentists or hotels across a city or district to size a market, plan sales territories, or scout competitors.
- **OpenStreetMap data extraction** — a simple front-end over the **OpenStreetMap API** (**Overpass** QL) that turns a place + category into clean JSON, with no GIS tooling and **no API key** required.

Keywords: OpenStreetMap API, Overpass, local business data, no API key, local lead generation, POI extraction, geocoding.

***

### Input

| Field | Type | Notes |
|---|---|---|
| `area` | string | **Required.** A place name to search inside, e.g. `"Shoreditch, London"` or `"Austin, Texas"`. Geocoded via Nominatim. |
| `categories` | array | Business categories, e.g. `["restaurant","cafe","dentist","gym"]`. Default `["restaurant","cafe"]`. Unknown categories fall back to a name search. |
| `maxResults` | integer | Cap how many businesses to return. Default `200`. |
| `aiEnrich` | boolean | Default `false`. If on, OpenAI adds a short positioning note per business (costs tokens, slows the run). |
| `model` | string | OpenAI model used only when `aiEnrich` is on. Default `gpt-4o-mini`. |

#### Minimal input example

```json
{
  "area": "Shoreditch, London",
  "categories": ["cafe", "restaurant"],
  "maxResults": 200
}
```

***

### Output example

```json
{
  "area": "Shoreditch, London",
  "name": "Ozone Coffee Roasters",
  "category": "cafe",
  "address": "Leonard Street 11",
  "city": "London",
  "postcode": "EC2A 4AQ",
  "phone": "+44 20 7490 1039",
  "website": "https://ozonecoffee.co.uk",
  "openingHours": "Mo-Fr 07:30-22:00; Sa-Su 09:00-22:00",
  "lat": 51.5247,
  "lon": -0.0836,
  "osmType": "node",
  "osmId": 1234567890,
  "osmUrl": "https://www.openstreetmap.org/node/1234567890",
  "categoryNote": null
}
```

Businesses with no `name` in OpenStreetMap are skipped. Address, phone and website appear only when the local mappers recorded them.

***

### Pay-per-event pricing

This Actor uses **pay-per-event** billing with a single event:

| Event | Charged when | Price |
|---|---|---|
| `area-searched` | **Once per run / area** — not per business. One charge covers geocoding + the Overpass query across all your categories, however many businesses come back. | **$0.20** |

Because OpenStreetMap data is free, the price reflects the orchestration and optional AI layer, not a per-place data cost. Running one area that returns 200 businesses costs a single `area-searched` charge.

***

### Data source

Data comes from **[OpenStreetMap](https://www.openstreetmap.org/)** via its free, public services: **Nominatim** (geocoding) and the **Overpass API** (POI query). No API key is required for either. OpenStreetMap data is licensed under the **Open Database License (ODbL)** — if you republish or display this data, please **attribute OpenStreetMap contributors**. The Actor sends a descriptive User-Agent and paces its requests politely.

***

### Setup

**No key needed** for the core list — geocoding and POI extraction run against free OpenStreetMap services out of the box.

`OPENAI_API_KEY` is only required if you turn on **`aiEnrich`** for the optional one-line positioning note per business. Without it (or with `aiEnrich` off), the Actor still returns the full business list.

***

### Use it from an AI agent (Apify MCP server)

This Actor is available through the [Apify MCP server](https://mcp.apify.com), so AI agents (Claude, ChatGPT, or anything that speaks MCP) can call it as a tool — hand it an `area` and `categories`, and read back the local businesses — with no custom integration code.

***

### Run it locally

```bash
npm install
## put your input in storage/key_value_stores/default/INPUT.json
export OPENAI_API_KEY=sk-...   # optional, only for aiEnrich
apify run -p
```

***

### Related actors

- [Google Maps Lead Enricher (AI)](https://apify.com/fuze/gmaps-lead-enricher) — Turn a pile of Google Maps results into sales-ready leads: emails, socials, website signals, AI score + opener.
- [Company Enrichment API (AI)](https://apify.com/fuze/ai-company-enrichment) — Turn a list of domains into structured company profiles: firmographics, contacts, socials and ICP fit.
- [B2B Email Verifier](https://apify.com/fuze/b2b-email-verifier) — Verify business email addresses: syntax, MX, deliverability.
- [Domain WHOIS Intelligence](https://apify.com/fuze/domain-whois-intelligence) — Registration, ownership and age signals for any domain.

# Actor input Schema

## `area` (type: `string`):

A place name to search inside, e.g. "Austin, Texas" or "Shoreditch, London". Geocoded via OpenStreetMap Nominatim.

## `categories` (type: `array`):

Business categories to find, e.g. restaurant, cafe, dentist, gym, bar, hotel, hairdresser, bakery. Unknown categories fall back to a name-based search.

## `maxResults` (type: `integer`):

Maximum number of businesses to return.

## `aiEnrich` (type: `boolean`):

If on, OpenAI adds a short positioning note per business. Costs tokens and slows the run. Off by default for a free, fast list.

## `model` (type: `string`):

Model used only when AI tagging is on (default gpt-4o-mini).

## Actor input object example

```json
{
  "area": "Shoreditch, London",
  "categories": [
    "restaurant",
    "cafe"
  ],
  "maxResults": 200,
  "aiEnrich": false
}
```

# Actor output Schema

## `businesses` (type: `string`):

All local businesses found in the default dataset.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "area": "Shoreditch, London",
    "categories": [
        "restaurant",
        "cafe"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("noniner/osm-local-business-finder").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "area": "Shoreditch, London",
    "categories": [
        "restaurant",
        "cafe",
    ],
}

# Run the Actor and wait for it to finish
run = client.actor("noniner/osm-local-business-finder").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "area": "Shoreditch, London",
  "categories": [
    "restaurant",
    "cafe"
  ]
}' |
apify call noniner/osm-local-business-finder --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,noniner/osm-local-business-finder"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/GXzApqWxh9ZDr98CR/builds/Atrjw5P1LPigpV9kl/openapi.json