Auto TS MCP Server

AutoTS is a time series package for Python designed for rapidly deploying high-accuracy forecasts at scale. Give it a try in your browser with the official demo app. It runs locally over stdio via the published package.

People who work with time series, machine learning and automl and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-25 · ★ 1,428 · #26 OF 106 MAINTAINED AI & ML · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Auto TS

Claude Code

claude mcp add winedarksea-autots -- uvx autots-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "winedarksea-autots": {
      "command": "uvx",
      "args": [
        "autots-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package autots-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.winedarksea is GitHub-verified and matches the repo owner

03 · What Auto TS can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

1.0.4 · 2026-08-20

1.0.4 🇺🇦 🇺🇦 🇺🇦 · more tuning of MCP download install · TVA optimizations and new features · Synthetic data minor new options · Feature detector and associated transformer bug fixes · Sounds the same as 1.0.3! But…

1.0.3 · 2026-04-15

1.0.3 🇺🇦 🇺🇦 🇺🇦 · more tuning of MCP download install · TVA optimizations · Synthetic data minor new options · Feature detector and associated transformer bug fixes

1.0.2 · 2026-03-30

1.0.2 🇺🇦 🇺🇦 🇺🇦 · more tuning of MCP download install · more optimization of MultivariateRegression · MLFlow logging function added (limited testing done) · MCP server breaking changes, async setup · MambaSSM…

04 · Who maintains Auto TS

AutoTS is maintained by winedarksea. It's the only MCP server we track from this author; the repo dates to Nov 2019.

05 · Facts

category
AI & ML - ranked #26 of 106 actively-maintained AI & ML servers as of 2026-09-18.
release cadence
1 release in the last 90 days (latest 2026-08-20)
registry
io.github.winedarksea/AutoTS (active, first published 2025-12-01 · 2 versions)
packages
pypi:autots-mcp

06 · Auto TS FAQ

What is Auto TS?

AutoTS is a time series package for Python designed for rapidly deploying high-accuracy forecasts at scale. Give it a try in your browser with the official demo app. It runs locally over stdio via the published package.

Is Auto TS still maintained?

Yes - as of 2026-09-18, its last commit was 2026-08-25 and it shipped 1 release in the last 90 days. We re-verify nightly.

How do I install Auto TS?

Run `uvx autots-mcp`. You can also paste the ready-made client config above.

Does Auto TS run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Auto TS