通过第一方 REST API 暴露 endplay 双明手计算的 MCP 服务器。MCP 进程是 HTTP 客户端，从不直接导入 Endplay。
double_dummy(pbn: str)
返回完整的 20 格赢墩表（N/E/S/W 庄家 × C/D/H/S/NT 花色）。
double_dummy_batch(pbns: list[str])
在一次调用中为多副牌返回相同的结果结构。
Related MCP server: TexasSolver MCP Server
cd c:/sw/bridge/ML-Contract-Bridge/src/endplay-dd-mcp-server
python -m venv .venv
.venv/Scripts/activate
pip install -e .先启动第一方 API，然后启动 MCP 客户端：
endplay-dd-api
# In another terminal:
endplay-dd-mcpMCP 服务器默认通过 stdio 运行。使用 ENDPLAY_DD_API_BASE_URL 配置其 API 端点（默认 http://127.0.0.1:8001）。
N:9642.95.AKQT4.K7 KJ3.K3.98.T98654 AQT85.Q862..AQJ2 7.AJT74.J76532.3{
"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}
}
}
}确保 endplay-dd-api 正在运行，然后在 MCP 配置中添加此服务器：
{
"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"
]
}
}
}This server cannot be deployed
Exact Texas Hold'em equity and hand analysis, every runout enumerated. Free, no API key.
Lichess public API: players, ratings, eval, tablebase, opening explorer
Negotiation math engine. Pareto frontier, counteroffer generation, zero LLM tokens.
Stockfish chess eval: best move, score, principal variation, multipv. $0.005/call via x402.
