GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
제작자가 쓴 설명(영어 원문)
MCP server for the start.gg GraphQL API: tournaments, events, entrants, sets, standings, streams
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.
STARTGG_TOKEN, STARTGG_ENABLE_WRITES비밀로 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": {
"startgg": {
"command": "npx",
"args": [
"-y",
"startgg-mcp-server"
],
"env": {
"STARTGG_TOKEN": "your-value",
"STARTGG_ENABLE_WRITES": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add startgg --env STARTGG_TOKEN=your-value --env STARTGG_ENABLE_WRITES=your-value -- npx -y startgg-mcp-server실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"startgg": {
"command": "npx",
"args": [
"-y",
"startgg-mcp-server"
],
"env": {
"STARTGG_TOKEN": "your-value",
"STARTGG_ENABLE_WRITES": "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": {
"startgg": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"startgg-mcp-server"
],
"env": {
"STARTGG_TOKEN": "your-value",
"STARTGG_ENABLE_WRITES": "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.
STARTGG_ENABLE_WRITES env이 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 GitHub 계정 tomo789 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
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: STARTGG_TOKEN
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(0.1.0)은 2개월 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Node.js도 있어야 해요.
같은 카테고리에는: GitHub, Desktop Commander, Cloudflare MCP
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
A Model Context Protocol server for the start.gg GraphQL API. It lets MCP clients (Claude Code, Claude Desktop, and others) discover tournaments, inspect events, entrants, sets, standings, and streams for any game on start.gg using natural language.
start.gg exposes a powerful but complex GraphQL API: entrants vs participants vs players, integer set states, complexity-limited pagination, epoch timestamps. This server wraps that API in a small set of MCP tools with:
{ round, state: "COMPLETED", entrant1: { gamerTag, seed }, score, winnerEntrantId, ... } instead of raw GraphQL nestingThe server is game-agnostic. Game-specific logic (e.g. Smash upset detection) belongs in applications built on top — see examples/smash-ultimate-watcher.
Retry-After supportAUTH_ERROR, RATE_LIMITED, NOT_FOUND, INVALID_INPUT, STARTGG_GRAPHQL_ERROR, NETWORK_ERROR, INTERNAL_ERRORgraphql/ files, separate from codeTreat the token like a password. This server reads it only from the STARTGG_TOKEN environment variable.
# run without installing
npx startgg-mcp-server
npm install -g startgg-mcp-server
Requires STARTGG_TOKEN in the environment; MCP clients normally launch it for you (see the next section).
git clone https://github.com/tomo789/startgg-mcp-server.git
cd startgg-mcp-server npm install npm run build
claude mcp add startgg --env STARTGG_TOKEN=YOUR_TOKEN -- npx -y startgg-mcp-server
Running from a source checkout instead:
claude mcp add startgg --env STARTGG_TOKEN=YOUR_TOKEN -- node /path/to/startgg-mcp-server/dist/cli.js
Add to claude_desktop_config.json:
{
"mcpServers": { "startgg": { "command": "npx", "args": ["-y", "startgg-mcp-server"], "env": { "STARTGG_TOKEN": "YOUR_TOKEN" } } } }
From a source checkout, use "command": "node" and "args": ["/path/to/startgg-mcp-server/dist/cli.js"] instead.
Any MCP client that supports stdio servers works the same way: run node dist/cli.js (or the startgg-mcp-server bin once installed via npm) with STARTGG_TOKEN set.
| Tool | Purpose |
|---|---|
search_videogames | Find videogame ids by name (e.g. "Super Smash Bros. Ultimate" → 1386) |
search_tournaments | General tournament search: name, videogame, country/state, date range, upcoming/past, open registration |
get_upcoming_tournaments | Tournaments that haven't ended yet (includes in-progress), soonest first, with a days window |
get_tournaments_by_videogame | Tournaments for one videogame id (upcoming / past / all) |
| Tool | Purpose |
|---|---|
get_tournament | Details, schedule, venue, events list, configured streams |
get_tournament_events | Events (brackets) of a tournament, optionally filtered by videogame |
get_tournament_entrants | Tournament-level participants (attendees); per-event seeding lives in get_event_entrants |
get_stream_queue | Stream queue: streams (with derived Twitch URLs) and the sets assigned to each |
| Tool | Purpose |
|---|---|
get_event | Event details including phases (Pools, Top 8, ...) with phase ids |
get_event_entrants | Entrants with seed, players, DQ flag; pagination or fetchAll |
get_event_standings | Placements (use perPage: 8 for Top 8) |
get_event_sets | Normalized sets with stream; filter by state, phase, round, entrants, players, VOD; includeGames for per-game details |
get_set_games | Per-game stage / winner / character picks for one set; see coverage note |
| Tool | Purpose |
|---|---|
get_player | Player by id: gamer tag, prefix, linked user |
get_player_sets | A player's recent sets across tournaments |
| Tool | Purpose |
|---|---|
resolve_startgg_url | start.gg URL/slug → { type, tournamentId, eventId, slugs, names } |
Tournament/event tools accept either a numeric id, a slug, or a full start.gg URL. Scheme-less URLs (start.gg/tournament/...) and /event/ slugs are accepted too — you rarely need resolve_startgg_url explicitly, but it is there when you want the ids.
{
"id": 106877974, "round": "Grand Final", "roundNumber": 3, "state": "COMPLETED", "stateRaw": 3, "completedAt": "2026-08-24T07:19:34.000Z", "entrant1": { "entrantId": 24480092, "name": "LittleMacMain", "seed": 5, "players": [{ "playerId": 3655189, "gamerTag": "LittleMacMain", "prefix": "" }], "score": 2 }, "entrant2": { "...": "same shape" }, "score": { "entrant1": 2, "entrant2": 3, "displayScore": "LittleMacMain 2 - RenSuø 3" }, "winnerEntrantId": 24481002, "phase": { "id": 1994001, "name": "Bracket" }, "vodUrl": null }
Notes grounded in the live API:
roundNumber < 0 means losers bracket; round is the human-readable name-1 is start.gg's disqualification marker"preview_3430499_2_0"state names are decoded from the integer stateRaw; both are always returnedentrant1/entrant2 use a players array, so doubles/teams work unchangedget_set_games (and get_event_sets with includeGames: true) add per-game details when start.gg has them:
{
"orderNum": 1, "winnerEntrantId": 24480092, "stage": { "id": 484, "name": "Small Battlefield" }, "selections": [{ "entrantId": 24481002, "character": { "id": 1846, "name": "Kazuya" } }] }
derivedCharacters summarizes unique character names per entrant in first-appearance order across games. This is derived, not an API field.
Character and stage data only exists when the set was reported with it. In a 2026-09 sample, late rounds (Top 8 / streamed) had it on about 90% of completed sets; early pools about 5%. An empty games array means not reported, not that no games were played. Typical flow: get_event_sets (e.g. phaseIds for Top 8) → pick set ids → get_set_games. For many sets at once, get_event_sets with includeGames: true.
Things to ask an MCP client once connected:
Find upcoming Super Smash Bros. Ultimate tournaments this week.
Get the entrants and seeds for this start.gg tournament URL: https://www.start.gg/tournament/.../event/...
Show me completed sets from Top 8 of that event.
Which streams are assigned to sets at this tournament?
What were the biggest seed upsets in this event?
A standalone example application (videogame lookup → upcoming tournaments → sets → upset candidates by seed difference) lives in examples/smash-ultimate-watcher.
| Variable | Required | Default | Purpose |
|---|---|---|---|
STARTGG_TOKEN | yes | — | start.gg API token |
STARTGG_ENABLE_WRITES | no | false | Reserved. No write tools exist yet; the flag only logs a notice |
STARTGG_RATE_LIMIT | no | 75 | Requests per 60s window (hard-capped at 80) |
STARTGG_TIMEOUT_MS | no | 30000 | Per-request HTTP timeout |
STARTGG_CACHE | no | on | Set off to disable the in-memory cache |
The API endpoint is deliberately not configurable through the environment: the token is only ever sent to api.start.gg. When using the client as a library (tests, tooling), inject apiUrl/fetchFn via the StartggClient constructor.
Out-of-range or non-numeric values for STARTGG_RATE_LIMIT / STARTGG_TIMEOUT_MS fall back to the default and log a warning on stderr.
Without STARTGG_TOKEN the server still starts and lists tools, but every call returns a clear AUTH_ERROR explaining how to fix it.
api.start.gg, and never included in tool output, logs, or error messages.env files are git-ignored; use .env.example as a templatestart.gg allows 80 requests per 60 seconds and at most 1000 objects per request. This server:
429 (honoring Retry-After) and transient 5xx errors with exponential backoff, at most 3 retries — GraphQL errors are never retriedperPage per tool so responses stay under the 1000-object complexity limit (sets are expensive: ~26+ objects each, hence perPage <= 30)fetchAll at 5 pages per tool (output is meant for an LLM context, so it stays around 100 KB of compact JSON) and reports truncated: true when it stops earlynpm run dev # run from source (tsx)
npm run build # compile to dist/ npm run
앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요