Oraclaw MCP Server

Your AI agent can't do math. OraClaw gives it deterministic optimization, simulation, forecasting, and risk analysis through the Model Context

Local serverstdioTypeScript

What is the Oraclaw MCP server?

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.

What the assistant can call

Once Oraclaw is connected, these are the calls the assistant has available:

  • 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

Configuration and credentials

You 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.

Setting it up

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.

Choosing this one

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.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Oraclaw.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the oraclaw mcp server does with a few real requests.

Available tools

ToolWhat it does
optimize_banditUCB1 / Thompson / Epsilon-Greedy arm selection
optimize_contextualContext-aware LinUCB bandit
optimize_evolveGenetic algorithm for discrete + multi-objective problems
solve_scheduleEnergy-matched task scheduling
score_convergenceMulti-source probability consensus (Hellinger)
score_calibrationBrier + log score for forecaster accuracy
predict_bayesianBeta posterior update from weighted evidence
predict_ensembleMulti-model consensus + uncertainty decomposition
plan_pathfindA* + Yen's k-shortest paths
simulate_montecarloSingle-factor Monte Carlo (6 distributions)
simulate_scenarioWhat-if comparison + sensitivity ranking
optimize_cmaesCMA-ES continuous black-box optimization
solve_constraintsLP / MIP / QP solver via HiGHS (provably optimal)
analyze_graphPageRank, Louvain communities, bottleneck detection

How to install the Oraclaw MCP server

{
  "mcpServers": {
    "oraclaw": {
      "command": "npx",
      "args": ["-y", "@oraclaw/mcp-server"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
ORACLAW_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Oraclaw to optimize bandit.
  • Use Oraclaw to optimize contextual.
  • Use Oraclaw to optimize evolve.

Frequently asked questions

It connects Oraclaw to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (optimize_bandit, optimize_contextual, optimize_evolve, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Oraclaw directly.