Google released TimesFM-3 on 31 August 2026. I shipped an MCP server for it the next day so Claude Desktop, Claude Code, and Cursor can call the model as a tool.
Repo: https://github.com/thenameisdevair/timesfm3-mcp
The tool is forecast(history, horizon)
.
You pass a chronological list of numbers. You get:
forecast
— median / point predictionquantiles
— the nine official TimesFM-3 heads, q10
through q90
TimesFM-3 already produced those quantile heads. Most thin wrappers throw them away. This one does not.
| Piece | License |
|---|---|
| This MCP wrapper | Apache-2.0 |
TimesFM-3 weights (google/timesfm-3.0-pytorch ) |
|
| non-commercial, non-production |
You can research, evaluate, and run agent experiments. You cannot put this checkpoint behind a paid API, a customer deliverable, or a live demand planner. Google’s commercial path is BigQuery / AlloyDB AI.FORECAST
.
If a README hides that, it is not a serious integration.
Weights are gated on Hugging Face. Accept the model terms first.
git clone https://github.com/thenameisdevair/timesfm3-mcp.git
cd timesfm3-mcp
python3 -m venv venv
source venv/bin/activate
pip install -r local/requirements.txt
pip install git+https://github.com/google-research/timesfm.git
huggingface-cli login
cd local && python client.py
Point Claude or Cursor at local/server.py using the venv Python. Config snippets are in the README.
No multivariate targets yet. No past/future covariates. No commercial backend. Those are next. This cut exists so “TimesFM-3 MCP” has a public, honest surface while the launch is still warm.
If the tool shape is wrong for your agent, feel free to open an issue on the repo.