/install codex-mcp-dev
Codex MCP Dev
Use the local Codex installation through the wrapper script at {baseDir}/scripts/codex_mcp.py.
This gives a stable path:
OpenClaw → mcporter → codex-mcp-server → local codex
Quick Setup
Install prerequisites first:
mcporter- local
codex codex-mcp
Create the project MCP entry if config/mcporter.json does not exist yet:
mcporter config add codex-cli --scope project --command codex-mcp
This skill expects a workspace-local MCP server named codex-cli.
Workflow
- Use this skill for non-trivial coding tasks.
- If it is the first use in a session or something looks broken, run:
python3 {baseDir}/scripts/codex_mcp.py doctor
- Choose a mode:
- Analysis / planning / explanation: use
askwithout--full-auto - Implementation / refactor / test-writing: use
ask --full-auto
- Analysis / planning / explanation: use
- Always set
--cwdto the target repo or project directory. - Give Codex a concrete prompt with files, constraints, and acceptance criteria.
- After Codex responds, inspect files and run local tests yourself when feasible instead of trusting the tool output blindly.
- Summarize changes, tests run, and any remaining risks.
Good Uses
- Implementing features across multiple files
- Fixing bugs with real repo context
- Refactoring with constraints
- Writing or updating tests
- Debugging failing commands or stack traces
- Asking local Codex for a second implementation pass or review
Command Patterns
Health check
python3 {baseDir}/scripts/codex_mcp.py doctor
Version info
python3 {baseDir}/scripts/codex_mcp.py version
Normal implementation
python3 {baseDir}/scripts/codex_mcp.py ask \
--cwd /absolute/path/to/repo \
--full-auto \
--prompt "Implement the requested change, update tests, and summarize what changed."
Read-only analysis
python3 {baseDir}/scripts/codex_mcp.py ask \
--cwd /absolute/path/to/repo \
--sandbox-mode read-only \
--approval-policy never \
--prompt "Explain the bug, identify likely root cause, and propose the smallest safe fix."
Long prompt from file
python3 {baseDir}/scripts/codex_mcp.py ask \
--cwd /absolute/path/to/repo \
--full-auto \
--prompt-file /tmp/codex-task.txt
Prompting Rules
Include as many of these as possible:
- Target files or directories
- Desired behavior
- Exact error messages or failing tests
- Constraints on scope
- Required test updates
- Expected output format
Prefer prompts like:
- "Fix the failing test in
tests/api.test.tswithout changing public behavior. Run the relevant tests and summarize the root cause." - "Refactor
src/cache.pyfor readability, keep behavior identical, and add regression tests for TTL edge cases." - "Review the auth flow in
server/and identify the top 3 correctness risks with concrete file references."
Guardrails
- Prefer
--full-autofor ordinary implementation work. - Do not use
--yolounless the user explicitly wants aggressive execution. - Use repo-specific
--cwd; do not run against the wrong directory. - Validate with local reads/tests when possible.
- If the task is tiny or surgical, skip this skill and edit directly.
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install codex-mcp-dev - 安装完成后,直接呼叫该 Skill 的名称或使用
/codex-mcp-dev触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
codex-mcp-dev 是什么?
Use the local Codex CLI through mcporter and codex-mcp-server for real coding work in the current project. Use when the user asks to build features, fix bugs... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 363 次。
如何安装 codex-mcp-dev?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install codex-mcp-dev」即可一键安装,无需额外配置。
codex-mcp-dev 是免费的吗?
是的,codex-mcp-dev 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
codex-mcp-dev 支持哪些平台?
codex-mcp-dev 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 codex-mcp-dev?
由 qiucen(@hollywood3)开发并维护,当前版本 v1.0.0。