timesfm-mcp 0.1.4

MCP server for Google's TimesFM 2.5 foundation model — give any AI agent zero-config time-series forecasting.

timesfm-mcp

MCP server for Google's TimesFM 2.5 — give any AI agent zero-config time-series forecasting.

Plug TimesFM 2.5, Google's 200M-parameter foundation model for time-series, directly into Claude Code, Claude Desktop, Cursor, or any MCP client. The agent calls forecast, gets point predictions + uncertainty bands + a trend/seasonality summary, and writes the explanation itself.

No ML configuration. No data pipelines. One line to run.

Chart generated with the statistical baseline. See "Enable TimesFM 2.5" below to use the full neural model.

Quickstart (30 seconds)

uvx timesfm-mcp        # runs over stdio for local agents

Add to your Claude Desktop / Claude Code / Cursor config:

{
  "mcpServers": {
    "forecast": { "command": "uvx", "args": ["timesfm-mcp"] }
  }
}

Then ask your agent: "Forecast the next 6 months from this revenue data and tell me what to expect."

Enable TimesFM 2.5 (optional, advanced)

TimesFM 2.5 is not on PyPI — install it from source, then install timesfm-mcp into the same environment:

git clone https://github.com/google-research/timesfm.git
cd timesfm && pip install -e ".[torch]"
pip install timesfm-mcp
timesfm-mcp

Requires ~16 GB RAM and downloads ~800 MB of model weights on first use. The server auto-detects TimesFM and upgrades to it automatically; no config change needed.

You don't need TimesFM to get started. uvx timesfm-mcp works instantly with the built-in statistical baseline — no download, no GPU, no extra install.

Two backends, zero config

Backend	When active	What it needs
TimesFM 2.5 (Google)	When installed	Install from source — see below
Statistical baseline	Always	Just NumPy — already a dependency

Tools

Tool	What it does
forecast	Forecast a single series with optional uncertainty bands
list_backends	Report which engine is active (timesfm / baseline)
backtest	Hold out the last N points — compare TimesFM vs baseline MAE/sMAPE

Documentation

Full docs in the docs/ folder:

• Getting Started — installation and first forecast
• Client Setup — Claude Desktop, Claude Code, Cursor configs
• Tool Reference — full parameter docs
• Cookbook — SaaS MRR, e-commerce demand, traffic, cloud spend
• How It Works — the math and model

Migrating from forecast-mcp

timesfm-mcp is the renamed continuation of forecast-mcp. Update your install:

pip install timesfm-mcp      # replaces: pip install forecast-mcp
uvx timesfm-mcp              # replaces: uvx forecast-mcp

Update your agent config: change "args": ["forecast-mcp"] → "args": ["timesfm-mcp"].

License

Apache-2.0