deepseek-claude-code-worker-mcp

Name: deepseek-claude-code-worker-mcp
Rating: 70 (1 reviews)
Author: louchi1984-coder

louchi1984-coder/deepseek-claude-code-worker-mcp

An MCP server that delegates heavy coding and file-editing tasks from Codex to DeepSeek via Claude Code, saving 40-60% of Codex main-thread tokens.

98 14MITUpdated 2026-05-29

Good

View on GitHub Open source file

Overview

The DeepSeek Code Worker MCP is designed to offload expensive code reading, editing, and checking tasks to DeepSeek V4 running through the Claude Code CLI. It provides asynchronous worker tools for managing background coding jobs, monitoring status, and validating changes while preserving token limits on the primary Codex orchestrator.

Capabilities

▸Asynchronous background coding workers
▸DeepSeek V4 integration via Claude Code launcher
▸Job lifecycle management (start, get, tail, wait, cancel)
▸Configurable safety modes and permission boundaries
▸Environment doctor and health checks

Best for

Delegating code implementation tasks from Codex to DeepSeek, Running automated debugging loops and multi-step agentic coding, Generating tests, scaffolding, and documentation without consuming main-thread context

Works with

CodexClaude Code

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%88 → +17.6

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%85 → +12.8

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%85 → +12.8

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%29 → +3.5

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%90 → +9.0

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%53 → +4.2

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 total69.8 / 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

Uses scoped Claude Code permissions by default with `bypassPermissions` disabled. Includes pre-tool-use hooks for blocking dangerous bash commands and out-of-scope writes, though it is not a complete container sandbox.