An MCP server that enables LLMs to discover, reason about, compose, and execute sktime estimator workflows via a registry-driven semantic engine.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.SKTIME_MCP_LOG_LEVEL— Server logging verbosity level (DEBUG, INFO, WARNING, ERROR). Defaults to WARNING.SKTIME_MCP_LOG_PATH— Optional file path to output logs to in addition to stderr (None)SKTIME_MCP_AUTO_FORMAT— Enables or disables automatic time-series formatting during data loading.SKTIME_MCP_JOB_MAX_AGE_HOURS— Maximum hours before completed background jobs are automatically pruned. Defaults to 24.SKTIME_MCP_JOB_CLEANUP_INTERVAL— Interval in seconds for periodic job cleanup checks 3600SKTIME_MCP_MAX_DATA_HANDLESSKTIME_MCP_MAX_RESPONSE_TOKENS— Maximum tokens allowed per tool response (e.g., 10000). If a response exceeds this limit, it is truncated and appended with a notice. Set to 0 (default) for unlimited.[](https://m8ven.ai/mcp/sktime-sktime-mcp-wuiyj0)