skforecast-ai — Claude Code MCP server: forecasts and setup
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.
claude mcp add skforecast-ai -- uvx skforecast-ai-mcpWhat skforecast-ai 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.
What it helps with
- 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 for the agent
- Forecast the time series in
data.csvusingyas the target,dateas 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.
How to install skforecast-ai
Platform CLI
claude mcp add skforecast-ai -- uvx skforecast-ai-mcpuvx runs the command named after the package; if the README names another one, use uvx --from skforecast-ai-mcp <command>
Platform CLI
codex mcp add skforecast-ai -- uvx skforecast-ai-mcpuvx runs the command named after the package; if the README names another one, use uvx --from skforecast-ai-mcp <command>
Config file
{
"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>
Config file
{
"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>
Platform CLI
gemini mcp add skforecast-ai uvx skforecast-ai-mcpuvx runs the command named after the package; if the README names another one, use uvx --from skforecast-ai-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about skforecast-ai
How do I install skforecast-ai in Claude Code?
Run claude mcp add skforecast-ai -- uvx skforecast-ai-mcp to add the MCP server.
What does skforecast-ai do?
It profiles a time series, selects a model using deterministic rules, validates it, and returns predictions, metrics, and a skforecast script.
Does forecasting require an API key?
No LLM is needed for forecasting. The optional LLM package adds explanations of results; it does not change the forecast.
