Control two local Codex CLI agents in parallel for secure development workflows.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "codex-master-mcp" yet — see the docs or source repo.
Start two Codex CLI agents: have Agent A refactor the user authentication module, and Agent B add unit tests for the payment API. Continuously report each status and provide a summary when done.
Status updates for both agents, each task result, and a merged final summary.
Check the current status of both agents; if one is idle, have it analyze the latest failed build log; if an agent is stuck for over 5 minutes, stop and restart it safely, then resume the task.
Agent status classification, logged recovery actions, and an analysis of the build failure cause.
Allow agents to work only within /workspace/app and /workspace/tests: have one agent fix a bug and the other update test files; if access to any other path is requested, reject it and explain why.
Task results completed within the allowed directories and rejection messages for unauthorized path access.
Connect IDEs or AI assistants to Codex CLI for safe automation and code analysis.
Get technical advice, code reviews, and explanations via Codex CLI.
Delegate coding tasks to Codex via MCP with security and result checks.
Run restartable multi-agent coding workflows with live monitoring and bug-finding control.
Enable Claude Code to perform coding tasks through the OpenAI Codex CLI.
Forward MCP tools to coding agents for session-based development tasks.