# AutoTS

Runs automated time series forecasting with genetic model search and probabilistic bounds. Useful when you need quick predictions directly in your assistant.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1434
- Author: winedarksea
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/winedarksea/AutoTS
- Updated: 2026-10-15
- HTML: https://affpapa.org/en/nevibecode/mcp/autots

## What it does

AutoTS searches for optimal forecasting pipelines over `pandas.DataFrame` inputs. It explores statistical methods, machine learning, and deep learning architectures while applying genetic algorithms to select feature transforms and ensembles. The tool natively handles multivariate series and external regressors.

The server runs via `uvx autots-mcp`. Default installation includes basic dependencies only, so specialized models require separate Python packages installed in your environment. Input tables work in either wide formats with datetime indexes or long three-column structures.

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

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- find the best forecasting pipeline using genetic search
- generate probabilistic predictions with upper and lower bounds
- build horizontal or mosaic ensembles across multiple series
- forecast multivariate time series with exogenous regressors

## Example prompts
- Forecast values 21 steps ahead from `metrics.csv` using fast models
- Fit an ensemble with a 0.9 prediction interval on this wide dataframe
- Find the best time series pipeline for long format data with series identifiers

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107423
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26559
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9366
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9289

---
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