endplay-dd-mcp-server
endplay-dd-mcp-server
MCP 서버는 자체 REST API를 통해 endplay 더블 더미 계산을 노출합니다. MCP 프로세스는 HTTP 클라이언트이며 Endplay를 직접 가져오지 않습니다.
Tools
double_dummy(pbn: str)
전체 20셀 트릭 테이블을 반환합니다 (N/E/S/W 선언자 x C/D/H/S/NT 스트레인).double_dummy_batch(pbns: list[str])
여러 딜을 한 번의 호출로 동일한 결과 형태로 반환합니다.
Related MCP server: gap
Setup
cd c:/sw/bridge/ML-Contract-Bridge/src/endplay-dd-mcp-server
python -m venv .venv
.venv/Scripts/activate
pip install -e .Run
자체 API를 시작한 다음 MCP 클라이언트를 실행하세요:
endplay-dd-api
# In another terminal:
endplay-dd-mcpMCP 서버는 기본적으로 stdio를 통해 실행됩니다. API 엔드포인트를 ENDPLAY_DD_API_BASE_URL로 구성하세요 (기본값 http://127.0.0.1:8001).
Example input
N:9642.95.AKQT4.K7 KJ3.K3.98.T98654 AQT85.Q862..AQJ2 7.AJT74.J76532.3Example output (shape)
{
"ok": true,
"pbn": "<input>",
"table": {
"denom_order": ["C", "D", "H", "S", "N"],
"player_order": ["N", "E", "S", "W"],
"by_declarer": {
"N": {"C": 8, "D": 8, "H": 7, "S": 7, "N": 9},
"E": {"C": 5, "D": 5, "H": 6, "S": 0, "N": 4},
"S": {"C": 8, "D": 7, "H": 7, "S": 7, "N": 9},
"W": {"C": 5, "D": 6, "H": 5, "S": 0, "N": 4}
}
}
}Cursor MCP config example
endplay-dd-api가 실행 중인지 확인한 후, MCP 구성에 이 서버를 추가하세요:
{
"mcpServers": {
"endplay-dd": {
"command": "c:/sw/bridge/ML-Contract-Bridge/src/endplay-dd-mcp-server/.venv/Scripts/python.exe",
"args": [
"-m",
"endplay_dd_mcp.server"
]
}
}
}Related MCP Connectors
Exact Texas Hold'em equity and hand analysis, every runout enumerated. Free, no API key.
Supported Balatro scoring and exact small-deck play/discard analysis with verified explanations.
Open chess platform where AI agents register, get matched and play each other. Referee only.
Lichess MCP — public read-only API for users, games, explorer, tablebase.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI agents to analyze shogi (Japanese chess) positions and moves by integrating with USI protocol engines. Provides position analysis, move evaluation, and game state assessment through HTTP API bridge and MCP tools.31MIT
- AlicenseAqualityCmaintenanceEnables any local AI agent to play turn-based games over MCP by exposing reset, observe, and act verbs with structured observations and validated legal actions.6MIT
- AlicenseCqualityBmaintenanceEnables an AI host to perform bounded Stockfish engine analysis, whole-game review, opening-knowledge lookup, tactical puzzles, and persistent position-specific tutoring sessions. It also supports graduated hints, spaced review, speech plans, and optional local synthesis or board-screenshot recognition over stdio or HTTP transports.58MIT
- AlicenseBqualityBmaintenanceEnables chess agents to query Stockfish evaluations (MultiPV, win/draw/loss probabilities, positional motifs) alongside a Neo4j positional graph of games and opening/endgame theory plus PostgreSQL telemetry. This lets the agent determine which moves are playable in a given position and deliver data-backed semantic coaching.62MIT