# easy-predict

The easy-predict MCP server forecasts the next number in a series and flags outliers. Use it when an agent needs basic analysis of numeric data.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 140 installs
- Author: rizzi-williams
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/rizzi-williams/easy-predict
- Updated: 2026-06-26
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/easy-predict

## What it does

easy-predict exposes `predict_timeseries` for forecasting the next point in a numeric series and `detect_anomalies` for spotting outliers with z-score analysis. Forecasting tests several options, including linear, `log1p`, last-delta, and mean, then picks a model through holdout evaluation.

Each call costs $0.01 USDC on Base and is settled through x402 micropayments. A Base wallet funded with USDC is required. The private key stays on the device, while the API receives only a signed payment header; a call cannot go through without wallet funds.

## Requirements
- Remote server: `https://easy-predict--rizzi-williams.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http easy-predict https://easy-predict--rizzi-williams.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add easy-predict --url https://easy-predict--rizzi-williams.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "easy-predict": {
            "url": "https://easy-predict--rizzi-williams.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "easy-predict": {
            "type": "http",
            "url": "https://easy-predict--rizzi-williams.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http easy-predict https://easy-predict--rizzi-williams.run.tools
```

## When to use it
- forecast the next value in a numeric series
- flag outliers in measured data
- return z-scores for suspicious points
- select a forecasting model through holdout evaluation

## Example prompts
- Use `predict_timeseries` to forecast the next value in this sales series.
- Run `detect_anomalies` on these measurements and return the z-scores.
- Analyze this numeric series, then report the selected forecasting model and its next-value estimate.

## Similar
- [lion-x402](https://affpapa.org/en/nevibecode/mcp/lion-x402.md) — MCP server · 3491 installs
- [AgentNDX](https://affpapa.org/en/nevibecode/mcp/agentndx.md) — MCP server · 4376 installs
- [DPX — AI Intelligence Oracle + Settlement Rail](https://affpapa.org/en/nevibecode/mcp/dpx-ai-intelligence-oracle-settlement-rail.md) — MCP server · 4355 installs
- [Spraay](https://affpapa.org/en/nevibecode/mcp/spraay.md) — MCP server · 1864 installs
- [FiatDock](https://affpapa.org/en/nevibecode/mcp/fiatdock.md) — MCP server · ★ 1 repo stars
- [databroker](https://affpapa.org/en/nevibecode/mcp/databroker.md) — MCP server

---
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
