Killbottleneck
Free-to-self-host goal and process maps for humans and AI agents, with REST API and MCP.
제작자가 쓴 설명(영어 원문)
Coordinates to places and streets, ZA addresses to points, and routes around your own geofences.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
ATLASFETCH_API_KEY비밀로 표시된 값은 내 계정의 열쇠예요. 절대 다른 사람과 공유하거나 채팅에 붙여 넣지 마세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"atlasfetch": {
"command": "npx",
"args": [
"-y",
"atlasfetch-mcp"
],
"env": {
"ATLASFETCH_API_KEY": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add atlasfetch --env ATLASFETCH_API_KEY=your-value -- npx -y atlasfetch-mcp실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"atlasfetch": {
"command": "npx",
"args": [
"-y",
"atlasfetch-mcp"
],
"env": {
"ATLASFETCH_API_KEY": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"atlasfetch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"atlasfetch-mcp"
],
"env": {
"ATLASFETCH_API_KEY": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검
레지스트리 이름이 도메인 atlasfetch.xyz 기준으로 확인되었어요(레지스트리가 도메인 소유를 확인해요)
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요
내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요
내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
입력해야 할 값: ATLASFETCH_API_KEY
내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.4.4)은 8일 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Node.js도 있어야 해요.
같은 카테고리에는: Killbottleneck, topo^alpin, Agent Data Tools: Everyday data
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Free-to-self-host goal and process maps for humans and AI agents, with REST API and MCP.
Avalanche bulletins, mountain weather, stations, huts, ski and snowshoe tours in the Alps.
25 tools: weather, time zones, sun and moon, earthquakes, countries. 25 free calls.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
No signup needed to try it: without a key it falls back to a shared public demo key, capped at 1,000 lookups a month across everyone using it. Get your own limits with a free sign-up at atlasfetch.xyz.
An MCP server for AtlasFetch — reverse geocoding to administrative boundaries and streets, and geofencing, as tools your AI assistant can call directly.
Ask "which municipality is -33.9249, 18.4241 in?" and get Cape Town, Western Cape, South Africa with ISO 3166 codes — from a real point-in-polygon lookup, not the model's memory.
country: United Kingdom (GB) · region: England (GB-ENG) · municipal: City of Westminster (GB-WSM)
| Tool | What it does |
|---|---|
lookup_location | A coordinate becomes the country, region and municipality containing it, with ISO 3166-1 / 3166-2 codes, plus matches from your own boundary sets. Optionally the nearest street (ask for the street layer), and the point as an H3 cell or Google Plus Code. |
geocode_address | An address becomes a point, in South Africa today, with a precision that says whether the house, the street or only the suburb was found — and what to do about it. |
get_route | A route between 2 and 25 coordinates by car, bike, foot or truck, with turn-by-turn steps — optionally around your own zones, or measuring how far it runs inside them. |
list_boundary_sets | Lists your boundary sets, their counts, and which API keys may query them. |
create_boundary_set | Creates an empty set for your own polygons. |
add_boundary | Adds one GeoJSON polygon, with properties returned on every match. |
update_boundary | Moves or reshapes one boundary, keeping its id, name and properties. |
Good for: reverse geocoding to administrative areas, finding the street a point is on, geofencing against your own delivery zones or service areas, jurisdiction and region checks, tagging location data with region codes, geocoding delivery addresses in South Africa, and routing that keeps out of the areas you name.
Not for: geocoding outside South Africa (yet), searching for places by name, traffic-aware ETAs, distance matrices, isochrones, map tiles, or downloading boundary geometry.
get_route returns distance, duration and turn-by-turn steps between 2 and 25 coordinates, for car, bike, foot or truck.
car: 3.5 km · 5 min · 11 steps · a location moved 62 m to reach a road — free-flow, no traffic
Three things worth knowing before you wire it up:
routeGeometry: "none"). An encoded polyline is thousands of characters an assistant cannot read; ask for polyline6 or geojson only when something will draw it.Your own zones, in a route. avoidSets names boundary sets to route *around*; exposureSets names sets to *measure* against, leaving the route alone and reporting how many metres of it ran inside each zone. A zone containing one of your locations cannot be avoided for that route — it is skipped, and the answer says so.
Plan limits apply: 2 locations on the free plans and up to 25 on Pro, truck is Pro only, and alternatives need exactly 2 locations. Over a cap the answer is a 403 and nothing is billed; a location with no road near it is a 422, and that one is billed, because the route was attempted.
geocode_address turns one address into a point — q on one line, or address already split into parts. South Africa today.
address · confidence 0.96 · 25 Adderley Street, Cape Town, ZA-WC — dispatch
street · confidence 0.47 · ambiguous · Long Street, Cape Town, ZA-WC — ask the customer before dispatching
Read the precision before you use the point. address is the house; interpolated is estimated between the numbers either side; intersection is a street corner ("Cnr Main Rd and Belmont Rd"); site is a named place such as a shopping centre, office park or hospital (pass the shop or unit number on to the driver); street is the right street but not the house; locality is only the suburb. The result line applies the API's own advice for deliveries: dispatch only on a house-, corner- or site-level answer that is not ambiguous, ask the recipient for a pin on a street-level one, and ask the customer when it is ambiguous, listing the other candidates by the suburb each lies in (five Long Streets in Cape Town: City Centre, Observatory, Maitland…). In South Africa most answers are street-level, because OpenStreetMap has house numbers on about 13% of street names.
One address per call, at 1 lookup each, found or not. That is deliberate: a delivery list goes through one row at a time, where you can see what it spends. Programs with thousands of rows should call POST /geocode/batch on the API directly.
Add the street layer and the answer includes the nearest street, and the house number where one is mapped. It is worldwide, and opt-in — not part of the default country, region, municipal.
You always get three answers — for 5 m, 20 m and unlimited — because "the nearest street" depends on how far you are willing to look:
"street": [
{ "radiusMeters": 5, "streetNumber": null, "streetName": "Adderley Street", "postcode": null, "distanceMeters": 2.7 }, { "radiusMeters": 20, "streetNumber": "25", "streetName": "Adderley Street", "postcode": "8001", "distanceMeters": 9.6 }, { "radiusMeters": null, "streetNumber": "25", "streetName": "Adderley Street", "postcode": "8001", "distanceMeters": 9.6 } ]
Two nulls that mean different things: "street": null means there is no street data for that country, while an entry whose fields are null means nothing was within that radius. streetNumber and postcode are strings (44A, 12-14, 0181); house numbers are rare outside well-mapped areas. Set streetGeometry and each answer also carries the street's line, trimmed to about 250 m — leave it off unless something will draw it.
claude mcp add atlasfetch -- npx -y atlasfetch-mcp
Add to your MCP config (claude_desktop_config.json, .cursor/mcp.json, or your client's equivalent):
{
"mcpServers": { "atlasfetch": { "command": "npx", "args": ["-y", "atlasfetch-mcp"], "env": { "ATLASFETCH_API_KEY": "your-key-here" } } } }
Requires Node 20 or newer.
The demo key is shared by every anonymous user on the internet — one pooled quota and rate limit. Fine for a first look, wrong for anything real.
Create your own at atlasfetch.xyz/dashboard and set ATLASFETCH_API_KEY. The free Personal plan needs no card. You can copy a key from the dashboard at any time — so restrict it to your own domains there. Keys made before 12 October 2026 were revoked; if yours stops working, copy a live one.
| Variable | Default | Purpose |
|---|---|---|
ATLASFETCH_API_KEY | *(demo key)* | Your API key. |
ATLASFETCH_API_URL | https://api.atlasfetch.xyz | Override only for local or staging APIs. |
`municipal` is the finest unit available, not a consistent kind of thing. Los Angeles returns a city; rural Kansas returns a county; some places return a district. Where a country's fine tier is patchy, a coarser complete tier answers instead, because a county beats null for most uses. Don't assume the value names a city.
A new boundary set cannot be made queryable from here. Sets are created switched off and granted to no key, and granting is addressed by API key *id* — which only a signed-in browser session can list. So this server can create a set and fill it, but the last step happens in the dashboard. create_boundary_set says so in its response rather than leaving you with a set that silently matches nothing.
A lookup or a geocoded address is one lookup; a route is 10 on the standard plans. A lookup is one, however many layers, sets or grid codes it touches. Metering happens before matching, so a lookup that matches nothing still counts. Requests rejected as invalid or rate-limited are not billed.
A few rules hold across all seven tools, so an input means the same thing wherever it appears.
add_boundary and update_boundary act on one set (set). lookup_location and geocode_address match against any number of sets (sets).avoid: { sets: [...] } and exposure: { sets: [...] }. The tool takes avoidSets and exposureSets, because a one-key wrapper object is a step a model gets wrong.routeGeometry on get_route, and streetGeometry on lookup_location and geocode_address. A plain geometry input is a polygon you send, on add_boundary and update_boundary. (get_route still accepts geometry as an old name for routeGeometry; it goes in 1.0.)| Tool | Input | This server | API | Why |
|---|---|---|---|---|
get_route | steps | true | false | Turn-by-turn is what someone asks an assistant for |
lookup_location | streetGeometry | adds street to base | 400 without street | Asking for a street's line means asking for the street |
— dispatch, — ask the customer), and its wording will keep improving. The JSON below it is the API's answer, unchanged, and that is what to parse.Before 1.0, minor versions (0.3 → 0.4) may rename or remove an input, as 0.4.0 did, though always with a deprecated alias first.
From 1.0:
intersection and site were added to precision), and the wording of descriptions and of the first line of each answer.Every release is described in CHANGELOG.md.
npm install
npm run build node scripts/smoke.mjs # drives the built server with a real MCP client, against the live API
MIT for this server. Reference boundaries derive from OpenStreetMap under the ODbL; attribution and share-alike obligations pass through to you. Coordinates you look up are not stored.