loading…
Search for a command to run...
loading…
Decision intelligence MCP server with 19 algorithms (bandits, Monte Carlo, constraint optimization, forecasting, anomaly detection, risk analysis, graph algorit
Decision intelligence MCP server with 19 algorithms (bandits, Monte Carlo, constraint optimization, forecasting, anomaly detection, risk analysis, graph algorithms), 12 MCP tools. Install via npx -y @oraclaw/mcp-server.
MIT License Tests MCP Algorithms Latency npm API Status Implementations
MCP Optimization Tools for AI Agents -- 12 tools, 19 algorithms, sub-25ms. Zero LLM cost.
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.
OraClaw's math has been independently implemented in 12 open-source projects across AI agent orchestration, time-series tracking, vector search, MIP optimization, and production ML systems -- all within the first 8 days after public launch.
Selected field implementations (see CHANGELOG.md for the full list):
codex/issue-367-linucb-router 1h40m after the spec correction.max_weight cap. Shipped in v0.1.3.Marketplace distribution:
Maintainer relationships (warm technical correspondence): Qdrant, Milvus, NetworkX, Apache DataFusion, DuckDB, pymc-labs.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"oraclaw": {
"command": "npx",
"args": ["-y", "@oraclaw/mcp-server"]
}
}
}
Then ask your agent:
"I have 3 email subject line variants. Which should I send next?"
The agent calls optimize_bandit and gets a statistically optimal selection in 0.01ms.
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},
{"id": "C", "name": "Option C", "pulls": 2, "totalReward": 1.8}
],
"algorithm": "ucb1"
}'
Response (<1ms):
{
"selected": { "id": "C", "name": "Option C" },
"score": 1.876,
"algorithm": "ucb1",
"exploitation": 0.9,
"exploration": 0.976,
"regret": 0.1
}
Free tier: 25 calls/day, no API key needed.
npm install @oraclaw/bandit
import { OraBandit } from '@oraclaw/bandit';
const client = new OraBandit({ baseUrl: 'https://oraclaw-api.onrender.com' });
const result = await client.optimize({
arms: [
{ id: 'A', name: 'Short Subject', pulls: 500, totalReward: 175 },
{ id: 'B', name: 'Long Subject', pulls: 300, totalReward: 126 },
],
algorithm: 'ucb1',
});
14 SDK packages: @oraclaw/bandit, @oraclaw/solver, @oraclaw/simulate, @oraclaw/risk, @oraclaw/forecast, @oraclaw/anomaly, @oraclaw/graph, @oraclaw/bayesian, @oraclaw/ensemble, @oraclaw/calibrate, @oraclaw/evolve, @oraclaw/pathfind, @oraclaw/cmaes, @oraclaw/decide
LLMs generate plausible text, not optimal solutions. Ask GPT to pick the best A/B test variant and it applies a heuristic that ignores the exploration-exploitation tradeoff. Ask it to solve a linear program and it hallucinates constraints. OraClaw gives your agent access to real algorithms -- bandits, solvers, forecasters, risk models -- that return mathematically correct answers in sub-millisecond time, without burning tokens on reasoning.
| Tool | What It Does | Latency |
|---|---|---|
optimize_bandit |
A/B test selection via UCB1, Thompson Sampling, Epsilon-Greedy | 0.01ms |
optimize_contextual |
Context-aware personalized selection via LinUCB | 0.05ms |
optimize_cmaes |
Black-box continuous optimization (CMA-ES) | 12ms |
solve_constraints |
LP/MIP/QP optimization via HiGHS solver | 2ms |
solve_schedule |
Energy-matched task scheduling | 3ms |
analyze_decision_graph |
PageRank, Louvain communities, bottleneck detection | 0.5ms |
analyze_portfolio_risk |
VaR and CVaR (Expected Shortfall) | <2ms |
score_convergence |
Multi-source agreement scoring | 0.04ms |
score_calibration |
Brier score and log score for prediction quality | 0.02ms |
predict_forecast |
ARIMA and Holt-Winters time series forecasting | 0.08ms |
detect_anomaly |
Z-Score and IQR anomaly detection | 0.01ms |
plan_pathfind |
A* pathfinding with k-shortest paths | 0.1ms |
14 of 17 REST endpoints respond in under 1ms. All under 25ms.
The API is live. No signup required.
# Bayesian inference
curl -X POST https://oraclaw-api.onrender.com/api/v1/predict/bayesian \
-H 'Content-Type: application/json' \
-d '{"prior": 0.3, "evidence": [{"factor": "positive_test", "weight": 0.9, "value": 0.05}]}'
# Monte Carlo simulation
curl -X POST https://oraclaw-api.onrender.com/api/v1/simulate/montecarlo \
-H 'Content-Type: application/json' \
-d '{"simulations": 1000, "distribution": "normal", "params": {"mean": 100, "stddev": 15}}'
# Anomaly detection
curl -X POST https://oraclaw-api.onrender.com/api/v1/detect/anomaly \
-H 'Content-Type: application/json' \
-d '{"data": [10, 12, 11, 13, 50, 12, 11, 10], "method": "zscore", "threshold": 2.0}'
| Tier | Calls | Price | Auth |
|---|---|---|---|
| Free | 25/day | $0 | None |
| Pay-per-call | 1K/day | $0.005/call | API key |
| Starter | 10K/mo | $9/mo | API key |
| Growth | 100K/mo | $49/mo | API key |
| Scale | 1M/mo | $199/mo | API key |
x402 USDC: AI agents pay $0.01-$0.15 per call with USDC on Base. No subscription, no API key.
| Component | Path |
|---|---|
| MCP Server | mission-control/packages/mcp-server/ |
| REST API | mission-control/apps/api/ |
| Algorithms | mission-control/apps/api/src/services/oracle/algorithms/ |
| SDK Packages | mission-control/packages/sdk/ |
| LangChain Tools | mission-control/integrations/langchain/oraclaw_tools.py |
| Mobile App | mission-control/apps/mobile/ |
| Dashboard (Next.js) | web/ |
We'd love to hear what you're working on. Share your use case, ask questions, or request features:
If this saved your agent from hallucinating math, star us :star:
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"whatsonyourmind-oraclaw": {
"command": "npx",
"args": []
}
}
}