Geocode a Place Name or Address to Coordinates, Typo-Tolerant (Photon, OpenStreetMap)
photon/geocode
Turn a place name or address into coordinates with the Photon geocoder over OpenStreetMap: each match as a GeoJSON feature with latitude and longitude, name, street, house number, postcode, city, state, country, OSM type and id, and a bounding box where it has one. Tolerates typos and partial text; names in the local language by default, or English, German or French. Optionally biases results toward a point with lat and lon together. Up to 20 results, best first; an unmatched query returns an empty list. © OpenStreetMap contributors (ODbL); cached for one hour. Passed through unmodified and served by Eden Engine; not an official product.
Price
$0.0026 per call
You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $5.
Data source
© OpenStreetMap contributors (https://www.openstreetmap.org/copyright), data under the Open Database Licence (ODbL), geocoded by Photon (Komoot). Served by Eden Engine; not an official OpenStreetMap or Komoot product.
Use it
Five steps: search, inspect, learn, run, settle. No per-tool setup; your agent reaches this tool through the meta-tools it already has.
Connect once and your AI can find and run this tool, and any other it needs.
// 1. search: find the tool
omnial_search({ query: "what you need" })
// 2. inspect: price and input schema
omnial_inspect({ tool: "photon/geocode" })
// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "photon/geocode" })
// 4. run: price the exact call first, then run it
omnial_execute({ tool: "photon/geocode", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "photon/geocode", input: { /* ... */ } })
// 5. settle: the call is charged when it finishes, nothing to doNot connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.
Pricing
Every charge this tool can incur.
| Charge | Price |
|---|---|
Per call | $0.0026 |
- Updated
- Oct 21, 2026
Input and output schemas
Input schema
{
"type": "object",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "The place name or address, for example berlin, Alexanderplatz or 10 Downing Street London."
},
"lat": {
"type": "number",
"maximum": 90,
"minimum": -90,
"description": "Latitude of a point to prefer results near. Give it together with lon."
},
"lon": {
"type": "number",
"maximum": 180,
"minimum": -180,
"description": "Longitude of a point to prefer results near. Give it together with lat."
},
"lang": {
"enum": [
"default",
"en",
"de",
"fr"
],
"type": "string",
"description": "Language of the place names: default (the local name), en, de or fr. Leave out for the local name."
},
"limit": {
"type": "integer",
"default": 5,
"maximum": 20,
"minimum": 1,
"description": "How many results to return, 1 to 20. Defaults to 5."
}
},
"additionalProperties": false
}Output schema
{
"type": "object",
"required": [
"features"
],
"properties": {
"type": {
"type": "string",
"description": "FeatureCollection."
},
"features": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string"
},
"geometry": {
"type": "object",
"description": "A GeoJSON Point; coordinates are [longitude, latitude].",
"additionalProperties": true
},
"properties": {
"type": "object",
"description": "name, street, housenumber, postcode, city, district, state, country, countrycode, osm_type (N node, W way, R relation), osm_id, osm_key, osm_value and extent where there is one.",
"additionalProperties": true
}
},
"additionalProperties": true
},
"description": "The matches, best first; empty when nothing matches."
}
},
"additionalProperties": true
}