Geocoding vs MCP Server
A side-by-side look at the Geocoding and MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Geocoding for location services work as a local process; choose MCP Server for location services as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Geocoding when
- You need dedicated capabilities in the Location Services domain.
- You prefer a local stdio subprocess transport.
- You want tools like
geocode, reverse_geocode, search_places.
Choose MCP Server when
- You need dedicated capabilities in the Location Services domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
STHAN_API_KEY. - You want tools like
sthan_verify_address, sthan_parse_address, sthan_autocomplete_address.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Location Services | Location Services |
| Quality signal | 59/100 · Good | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | Freemium |
| Required env vars | None listed | STHAN_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 0 |
| Directory activity | 4 views 0 installs 0 upvotes | 5 views 0 installs 0 upvotes |
| Tools | 4 | 8 |
| Full listing | View Geocoding | View MCP Server |
Tools & capabilities
Geocoding tools 4
geocodeConvert an address, place name, or landmark into geographic coordinates. Use this tool when: - The user gives a place/address and you need its latitude/longitude - You need to disambiguate a place name (returns ranked matches) - You need a place's coordinates before another geo operation Args: query: Address, place name, or landmark. limit: Max results. country_codes: Optional ISO country filter. response_format: 'markdown' or 'json'. Returns: str: Ranked matches with coordinates, type, and full display name. Example: Input: {"query": "Eiffel Tower"} Output: 48.8584, 2.2945 — Tour Eiffel, Paris, Francereverse_geocodeConvert geographic coordinates into a human-readable address. Use this tool when: - The user gives latitude/longitude and wants to know what's there - You have coordinates (e.g. from geocode) and need the address Args: latitude: Latitude (-90 to 90). longitude: Longitude (-180 to 180). response_format: 'markdown' or 'json'. Returns: str: The address/place at those coordinates, with structured components. Example: Input: {"latitude": 48.8584, "longitude": 2.2945} Output: Avenue Anatole France, Paris, Francesearch_placesSearch for places or points of interest by description, with coordinates. Like geocode, but oriented toward finding multiple matching places/POIs (shops, landmarks, amenities) rather than resolving one address. Use this tool when: - The user wants places of a kind in an area ("parks in Austin") - The user wants options, not a single precise address Args: query: What to find, optionally including a location. limit: Max places. country_codes: Optional ISO country filter. response_format: 'markdown' or 'json'. Returns: str: Matching places with coordinates and type. Example: Input: {"query": "bookstores in Paris", "limit": 5} Output: Up to 5 bookstores with names and coordinatesdistance_betweenCompute the straight-line (great-circle) distance between two places. Geocodes both endpoints, then computes the as-the-crow-flies distance. (This is not driving/route distance.) Use this tool when: - The user asks how far apart two places are - You need a quick distance between two named locations Args: origin: Start place or address. destination: End place or address. unit: 'km' or 'miles'. response_format: 'markdown' or 'json'. Returns: str: The distance, plus the resolved coordinates of each endpoint. Example: Input: {"origin": "Paris", "destination": "Berlin"} Output: ~878 km between Paris and Berlin
MCP Server tools 8
sthan_verify_addressVerify a US address is real and deliverable. Returns standardized format, ZIP+4, DPV, residential/commercial.sthan_parse_addressParse freeform US address text into structured components (street number, name, type, direction, unit, city, state, zip).sthan_autocomplete_addressSuggest complete US addresses from partial input. Sub-100ms.sthan_autocomplete_citySuggest US cities from partial input, with state code.sthan_autocomplete_zipcodeSuggest US ZIP codes from partial input.sthan_geocodeUS address → latitude/longitude with accuracy + confidence, county, ZIP+4 and time zone.sthan_reverse_geocodeLatitude/longitude → nearest US street address with distance in meters, county, ZIP+4 and time zone; `limit` (up to 10) also lists nearby addresses.sthan_ip_geolocationIPv4 or IPv6 → location (country to postal code, local time, flag, currency), the network behind it (ASN, ISP, proxy/hosting flags) and a confidence score.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Geocoding
{
"mcpServers": {
"geocoding": {
"command": "npx",
"args": [
"-y",
"geocode-mcp"
]
}
}
}
MCP Server
{
"mcpServers": {
"sthan-io-mcp-server": {
"command": "npx",
"args": [
"-y",
"@sthan/mcp-server"
],
"env": {
"STHAN_API_KEY": "YOUR_STHAN_API_KEY_HERE"
}
}
}
}
Frequently asked questions
Geocoding is categorized under Location Services and uses a local stdio subprocess. MCP Server belongs to Location Services and uses a local stdio subprocess. Pick Geocoding for location services work and MCP Server for location services.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Geocoding has no declared pricing — check the project's own site. MCP Server is listed as freemium — a free tier with paid plans. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add geocoding and sthan-io-mcp-server as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Geocoding has a quality signal of 59/100 (Good) with 4 views, 0 installs and 1 GitHub stars. MCP Server has 61/100 (Good) with 5 views, 0 installs and 0 GitHub stars.