Your AI agent can't do math. OraClaw gives it deterministic optimization, simulation, forecasting, and risk analysis through the Model Context
Oraclaw MCP server exists for a simple reason — assistants are far more useful when they can act on Oraclaw directly instead of describing what you should do. Your AI agent can't do math. OraClaw gives it deterministic optimization, simulation, forecasting, and risk analysis through the Model Context Protocol. Every tool returns structured JSON, runs in under 25ms, and costs nothing to compute.
Once Oraclaw is connected, these are the calls the assistant has available:
optimize_bandit — UCB1 / Thompson / Epsilon-Greedy arm selectionoptimize_contextual — Context-aware LinUCB banditoptimize_evolve — Genetic algorithm for discrete + multi-objective problemssolve_schedule — Energy-matched task schedulingscore_convergence — Multi-source probability consensus (Hellinger)score_calibration — Brier + log score for forecaster accuracypredict_bayesian — Beta posterior update from weighted evidencepredict_ensemble — Multi-model consensus + uncertainty decompositionplan_pathfind — A* + Yen's k-shortest pathssimulate_montecarlo — Single-factor Monte Carlo (6 distributions)simulate_scenario — What-if comparison + sensitivity rankingoptimize_cmaes — CMA-ES continuous black-box optimizationYou will need one environment variable: ORACLAW_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Installation goes through your MCP client rather than a global install: point it at @oraclaw/bandit on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Among the planning and project tracking options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Oraclaw's toolset — optimize_bandit, optimize_contextual, optimize_evolve and 11 more — is a fair guide to whether it matches your workflow. It is maintained by whatsonyourmind; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| optimize_bandit | UCB1 / Thompson / Epsilon-Greedy arm selection |
| optimize_contextual | Context-aware LinUCB bandit |
| optimize_evolve | Genetic algorithm for discrete + multi-objective problems |
| solve_schedule | Energy-matched task scheduling |
| score_convergence | Multi-source probability consensus (Hellinger) |
| score_calibration | Brier + log score for forecaster accuracy |
| predict_bayesian | Beta posterior update from weighted evidence |
| predict_ensemble | Multi-model consensus + uncertainty decomposition |
| plan_pathfind | A* + Yen's k-shortest paths |
| simulate_montecarlo | Single-factor Monte Carlo (6 distributions) |
| simulate_scenario | What-if comparison + sensitivity ranking |
| optimize_cmaes | CMA-ES continuous black-box optimization |
| solve_constraints | LP / MIP / QP solver via HiGHS (provably optimal) |
| analyze_graph | PageRank, Louvain communities, bottleneck detection |
{
"mcpServers": {
"oraclaw": {
"command": "npx",
"args": ["-y", "@oraclaw/mcp-server"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| ORACLAW_API_KEY | Credential the server authenticates with. | Yes |
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.