Oraclaw

io.github.WhatsonyourmindPublished by GitHub account Whatsonyourmindv1.5.1Updated Oct 24, 2026

Decision intelligence MCP — 17 tools (optimize, simulate, predict, score, graph). Sub-25ms.

VerifiedSTDIODesktop onlyData & AnalyticsAI & ML

Overview

AI-generated overview

Gives an assistant 17 deterministic decision-intelligence tools for bandit selection, optimization, simulation, forecasting, scoring, and graph analysis.

What you can do
OraClaw exposes 17 algorithmic tools that return structured JSON instead of letting the model do math itself. Free tools cover bandit and contextual bandit arm selection, genetic optimization, scheduling, probability consensus and calibration scoring, Bayesian and ensemble prediction, A* pathfinding, Monte Carlo simulation, and scenario comparison. Premium tools add CMA-ES optimization, LP/MIP/QP constraint solving, graph analytics, portfolio risk measures, time-series forecasting, and anomaly detection. Each tool declares input and output schemas plus MCP behavior annotations.
When to use it
Useful when an assistant must choose between options from observed results, solve scheduling or routing problems, run what-if simulations, forecast a series, or rank graph nodes, and you want a real algorithm rather than a model-generated formula. The free tier covers the common selection and simulation cases; the premium tier is for continuous optimization, constraint solvers, risk, and forecasting.
Requirements
Runs locally over stdio, typically launched with npx from the npm package @oraclaw/mcp-server, so Node.js and network access are needed. No authentication is required for the 11 free tools. Premium tools need an API key supplied through the ORACLAW_API_KEY environment variable. Desktop MCP clients only.
Before you install
Premium tools require the ORACLAW_API_KEY secret, and the README states pay-per-call pricing at $0.005 per call with a 1,000 calls/day cap, or a $9/month Starter plan, so usage can cost money. Tool calls are sent to the provider's remote API endpoint, so inputs leave the machine. The README also documents a direct HTTP API with a free tier of 25 calls/day per IP.

Installation

In SourceWeft

  1. Open Oraclaw in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

OraClaw MCP Server

17 decision-intelligence tools your AI agent can call. Sub-25ms. 11 free without a key.

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

Drop that into your Claude Desktop / Cursor / Cline MCP config and your agent can immediately:

"I have 3 email subject line variants with these click rates. Which should I send next?"

The agent calls optimize_bandit → gets a statistically optimal arm in 0.01ms:

{ "selected": { "id": "C", "name": "Option C" },  "score": 1.876, "exploitation": 0.9, "exploration": 0.976, "regret": 0.1 }

No LLM math, no hallucinated formulas, no setup beyond the snippet above.

All 17 tools

Free (no key)What it does
optimize_banditUCB1 / Thompson / ε-greedy arm selection
optimize_contextualLinUCB contextual bandit (per-situation choice)
optimize_evolveGenetic algorithm (discrete + multi-objective)
solve_scheduleTask → time-slot assignment with energy matching
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
Premium (need API key)What it does
optimize_cmaesCMA-ES continuous black-box optimization
solve_constraintsLP / MIP / QP solver (HiGHS, provably optimal)
analyze_graphPageRank + Louvain + critical path + bottlenecks
analyze_riskPortfolio VaR / CVaR with correlation
predict_forecastARIMA / Holt-Winters time series
detect_anomalyZ-score / IQR outlier detection

Every tool ships with an explicit inputSchema, outputSchema, and MCP behavior annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) so your agent knows exactly what it gets back.

Get a key for premium tools

oraclaw signup → — one email field, instant key, no card needed. 1,000 calls/day on pay-per-call ($0.005/call). Upgrade to Starter $9/mo for 50k/month.

Then add ORACLAW_API_KEY to your MCP env:

json
{  "mcpServers": {    "oraclaw": {      "command": "npx",      "args": ["-y", "@oraclaw/mcp-server"],      "env": { "ORACLAW_API_KEY": "your-key-here" }    }  }}

Use the API directly (no MCP)

bash
curl -X POST https://oraclaw-api.onrender.com/api/v1/optimize/bandit \  -H "Content-Type: application/json" \  -d '{    "arms": [      {"id":"A", "name":"Option A", "pulls":10, "totalReward":7},      {"id":"B", "name":"Option B", "pulls":10, "totalReward":5}    ],    "algorithm": "ucb1"  }'

Free tier: 25 calls/day per IP, no key required.

Why agents need this

LLMs can't reliably do: bandit selection, LP optimization, time-series forecasting, graph centrality, Monte Carlo sampling, or anomaly detection. They confabulate the math. OraClaw is the deterministic substrate underneath your agent — every answer is a real algorithm, returns structured JSON, and runs in under 25ms.

Source: mission-control/packages/mcp-server/README.md at commit 2d8ea96

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.5.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts