Oraclaw
未认领Deterministic decision-intelligence MCP server for AI agents — 17 tools (bandits/LinUCB, HiGHS LP/MIP, PageRank, Monte Carlo, CMA-ES, conformal). Sub-25ms. Zero LLM cost. 11 free, no key. Listed on the MCP Registry & Glama.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'oraclaw' -- 'npx' '-y' '@oraclaw/bandit'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
17 个工具中显示 17 个
文档中列出的工具 (17)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
analyze_graph
PageRank, Louvain communities, bottleneck detection
analyze_risk
VaR and CVaR (Expected Shortfall)
detect_anomaly
Z-Score + IQR anomaly detection
optimize_bandit
UCB1 / Thompson / Epsilon-Greedy arm selection
optimize_cmaes
CMA-ES continuous black-box optimization
optimize_contextual
Context-aware LinUCB bandit
optimize_evolve
Genetic algorithm for discrete + multi-objective problems
plan_pathfind
A + Yen's k-shortest paths
predict_bayesian
Beta posterior update from weighted evidence
predict_ensemble
Multi-model consensus + uncertainty decomposition
predict_forecast
ARIMA + Holt-Winters time series forecasting
score_calibration
Brier + log score for forecaster accuracy
score_convergence
Multi-source probability consensus (Hellinger)
simulate_montecarlo
Single-factor Monte Carlo (6 distributions)
simulate_scenario
What-if comparison + sensitivity ranking
solve_constraints
LP / MIP / QP solver via HiGHS (provably optimal)
solve_schedule
Energy-matched task scheduling