$ loading_
Delegate exploration and implementation tasks to DeepSeek with subagents and persistence.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Codex DeepSeek Delegate MCP" yet — see the docs or source repo.
Use Codex DeepSeek Delegate MCP to analyze this Python service, find duplicated logic, and delegate the refactoring work to suitable subagents. Keep the current API behavior unchanged and return a refactoring plan, key changes, and suggested commit steps.
A phased refactoring plan, subagent task assignments, and actionable implementation guidance.
Using Codex DeepSeek Delegate MCP, create a persistent task for technical exploration and implementation breakdown of a new 'permission audit log' feature. Track task state for later continuation and report current progress, next steps, and open questions.
A persistent task record plus a progress summary, next actions, and identified risks.
Use Codex DeepSeek Delegate MCP to launch multiple subagents to research vector database options, deployment costs, and performance benchmarks, then consolidate the results into a technical decision recommendation with a clear final choice and rationale.
A consolidated research report by topic and an evidence-based technology recommendation.
Run Codex models through a persistent MCP server without sharing ChatGPT credentials.
Delegate Claude Code subagents to local or external model backends seamlessly.
Offload heavy code reading, editing, and checking to DeepSeek efficiently.
Delegate implementation tasks from AI coding agents to the Codex CLI.
Delegate coding and debugging from Claude Code to OpenAI Codex with auto-recovery.
Use Codex in Claude Code for execution, debugging, and web search.