sktime-mcp
OfficialRelated Servers
Alternatives to sktime-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceA server that enables seamless integration between local Ollama LLM instances and MCP-compatible applications, providing advanced task decomposition, evaluation, and workflow management capabilities.6-
- AlicenseNot gradedqualityCmaintenanceAn MCP server for domain-agnostic task orchestration, turning objectives into executed workflows with built-in validation, security, and multi-agent patterns.Apache 2.0
- FlicenseNot gradedqualityFmaintenanceA production-ready MCP server built with FastAPI, providing an enhanced tool registry for creating, managing, and documenting AI tools for Large Language Models (LLMs).34-
- AlicenseNot gradedqualityDmaintenanceMCP server for interacting with Conductor workflow orchestration, enabling AI agents to create, execute, and analyze workflows.Apache 2.0
- AlicenseAqualityBmaintenanceAn MCP server that exposes deterministic workflows as tools, allowing small models to reliably orchestrate APIs and other MCP servers with minimal parameters.221 npm2MIT
- AlicenseAqualityAmaintenanceA universal MCP server that enables any LLM or AI agent to access expert skills from your local filesystem.3525 npm39MIT
TDQS
Scored across 26 tools
Several tools have overlapping purposes, such as 'list_available_data' and 'list_handles' (different but similar names), 'release_data_handle' and 'release_handle', and 'describe_component' and 'query_registry'. The generic 'call_method' tool also overlaps with standard fitting/prediction tools, though it is intended for non-standard cases. Overall, an agent might occasionally confuse tools despite descriptive names.
Most tool names follow a consistent 'verb_noun' pattern in snake_case (e.g., 'load_data_source', 'inspect_data', 'split_data'). However, a few short verbs like 'fit', 'predict', and 'update' break this pattern, and there is slight inconsistency with longer names like 'release_data_handle' vs 'release_handle'. Overall, the naming is mostly predictable.
With 26 tools, the server is on the higher end of appropriate size. It covers many aspects of time series forecasting (data handling, modeling, evaluation, plotting, job management), but some tools like 'run_command' and 'call_method' are generic escapes. The count feels slightly heavy but not excessive for the domain.
The tool surface covers the core workflow for time series forecasting: data loading, inspection, splitting, transformation, model instantiation, fitting, prediction, updating, evaluation, and saving/loading. Additionally, it supports plotting, code export, registry queries, and async job management. Minor gaps include a lack of explicit deletion for persistent models/data and hyperparameter tuning, but these are not critical.