# oraclaw

Adds decision tools for optimization, forecasting, simulation, and graph analysis to AI agents. Use it when a choice needs calculated evidence.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 13
- Author: Whatsonyourmind
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Whatsonyourmind/oraclaw/tree/HEAD/mission-control/packages/mcp-server
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/mcp/oraclaw

## What it does

\`oraclaw` gives an agent callable tools for selecting options, scheduling work, updating predictions, testing scenarios, and examining graph structure. Available functions include `optimize_bandit`, `solve_schedule`, `predict_bayesian`, `simulate_montecarlo`, and `plan_pathfind`.

The server runs with `npx -y @oraclaw/mcp-server`. Each tool exposes input and output schemas plus MCP behavior hints, so the client can handle structured JSON results. It can be connected to Claude Code, Codex, Cursor, and the other listed clients.

Free tools work without a key. Premium calls require `ORACLAW_API_KEY`, so those functions will fail until the variable is added to the MCP configuration.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `ORACLAW_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add oraclaw -e ORACLAW_API_KEY=<ORACLAW_API_KEY> -- npx -y @oraclaw/mcp-server
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add mcp-server --env ORACLAW_API_KEY=<ORACLAW_API_KEY> -- npx -y @oraclaw/mcp-server
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "@oraclaw/mcp-server"
            ],
            "env": {
                "ORACLAW_API_KEY": "<ORACLAW_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mcp-server": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@oraclaw/mcp-server"
            ],
            "env": {
                "ORACLAW_API_KEY": "<ORACLAW_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e ORACLAW_API_KEY=<ORACLAW_API_KEY> mcp-server npx -y @oraclaw/mcp-server
```
Replace <…> with your own values

## When to use it
- select an option from observed rewards
- update a probability estimate from evidence
- compare scenarios and rank sensitivities
- assign tasks to suitable time slots
- find routes through a graph

## Example prompts
- Use `optimize_bandit` to choose the next option from these reward totals.
- Run `simulate_scenario` on these alternatives and rank the factors by sensitivity.
- Update the estimate with `predict_bayesian` using these observations.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md