# skforecast-ai

This MCP server forecasts time series from CSV files and returns the results with a skforecast script. Use it to inspect a forecast and the decisions behind it.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 52
- Author: skforecast
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/skforecast/skforecast-ai
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/skforecast-ai

## What it does

skforecast-ai profiles a time series, selects a model through deterministic rules, tests it on held-out data, and produces a forecast. The result includes predictions, evaluation metrics, and a standalone skforecast script. Its profile and plan expose the choices made along the way. The same input data leads to the same rule-based choices.

Connect the server to Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, or Zed. The Claude Code setup command runs `skforecast-ai-mcp` with `uvx`. There is also a Python package, which requires Python 3.10 or newer. Forecasting works without an LLM; the optional LLM layer explains a completed result and does not alter it.

The command-line interface can create a forecast with `skforecast-ai forecast`, using a CSV file, target field, date column, and forecast horizon. With the optional LLM package installed, `ask()` can explain metrics or model selection. It sends only the result’s predictions and metrics, not the dataset.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add skforecast-ai -- uvx skforecast-ai-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from skforecast-ai-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add skforecast-ai -- uvx skforecast-ai-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from skforecast-ai-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "skforecast-ai": {
            "command": "uvx",
            "args": [
                "skforecast-ai-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from skforecast-ai-mcp <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "skforecast-ai": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "skforecast-ai-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from skforecast-ai-mcp <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add skforecast-ai uvx skforecast-ai-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from skforecast-ai-mcp <command>

## When to use it
- forecast a time series from a CSV file
- evaluate a model on held-out data
- generate a standalone skforecast script
- explain why a forecasting model was selected

## Example prompts
- Forecast the time series in `data.csv` using `y` as the target, `date` as the date column, and a 12-step horizon.
- Run a forecast and show the metrics from the held-out evaluation.
- Explain why this model was selected for the forecast.

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27669
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49845

---
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