#
ENJA

Whale

MCP Server

usewhale/Whale

Whale is a terminal-based AI coding agent optimized for DeepSeek, featuring a high prompt-cache hit rate, dynamic JavaScript workflows, and Model Context Protocol (MCP) support.

937 69MITUpdated 2026-08-11

Overview

Whale provides a blazingly fast, DeepSeek-native AI coding assistant that operates directly in the terminal through an interactive TUI, single-shot CLI commands, or a headless mode for CI/CD pipelines. It leverages aggressive prompt caching to drastically reduce costs while supporting modular extensibility through custom skills, plugins, hooks, and MCP servers.

Capabilities

  • DeepSeek-native tool calling and long context handling
  • JavaScript-powered dynamic multi-agent orchestration
  • Model Context Protocol (MCP) server integration
  • Interactive terminal user interface (TUI)
  • Single-shot CLI questions and code reviews
  • Headless CI/CD automation mode
  • Customizable skills, subagents, plugins, and lifecycle hooks

Best for

Executing multi-agent research and code review pipelines using JavaScript-based dynamic workflows., Performing interactive software development and bug fixing directly within the terminal., Automating code reviews, pull request assessments, and scheduled tasks in CI/CD via headless execution.

Works with

CodexClaude Code
Evoa Score breakdown= Σ (score × weight)
78
Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 GitHub 最終push日時の新しさ

Documentation12%41 → +4.9

ドキュメントの充実度・分かりやすさ。 README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 AIによる独自性判定

Popularity8%76 → +6.1

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%50 → +2.5

対応AIエージェントの広さ。 AIによる対応エージェント判定

Weighted total78.0 / 100

ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

Exercise caution with project lifecycle hooks, as they can execute arbitrary shell commands. Ensure local configuration files, session logs, and API keys stored under configuration directories are kept private.

Categories

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.