Python time series forecasting assistant built on skforecast: deterministic decisions, the script that ran, an optional LLM that explains them, and an MCP server for AI agents.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add skforecast-ai -- uvx skforecast-ai-mcp --allow-dir '<ALLOW_DIR>'~/.codex/config.toml
[mcp_servers.skforecast-ai]
command = "uvx"
args = ["skforecast-ai-mcp", "--allow-dir", "<ALLOW_DIR>"]
# codex mcp add skforecast-ai -- uvx skforecast-ai-mcp --allow-dir '<ALLOW_DIR>'~/.cursor/mcp.json
{
"mcpServers": {
"skforecast-ai": {
"command": "uvx",
"args": [
"skforecast-ai-mcp",
"--allow-dir",
"<ALLOW_DIR>"
]
}
}
}.vscode/mcp.json
{
"servers": {
"skforecast-ai": {
"type": "stdio",
"command": "uvx",
"args": [
"skforecast-ai-mcp",
"--allow-dir",
"<ALLOW_DIR>"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"skforecast-ai": {
"command": "uvx",
"args": [
"skforecast-ai-mcp",
"--allow-dir",
"<ALLOW_DIR>"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"skforecast-ai": {
"command": "uvx",
"args": [
"skforecast-ai-mcp",
"--allow-dir",
"<ALLOW_DIR>"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"skforecast-ai": {
"command": "uvx",
"args": [
"skforecast-ai-mcp",
"--allow-dir",
"<ALLOW_DIR>"
]
}
}
}