codex-bridge
A lightweight MCP server bridging AI agents to OpenAI models via official CLI
File Explorer
Download Latest Version (.zip)- bug_report.yml
- config.yml
- feature_request.yml
- ci.yml
- release.yml
- pull_request_template.md
- __init__.py
- __main__.py
- mcp_server.py
- README.md
- test_mcp_tools.py
- TEST_RESULTS.md
- .gitignore
- CHANGELOG.md
- CLAUDE.md
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- Dockerfile
- LICENSE
- pyproject.toml
- README.md
- RELEASE_NOTES_v1.2.1.md
- SECURITY.md
# Installation Guide
git clone https://github.com/eLyiN/codex-bridge
Downloads the entire project code from GitHub to your computer.
cd codex-bridge
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommendednpm install -g @openai/codex-cli
Installs the package published on the npm registry globally β no need to clone the source.
pip install codex-bridge
Installs the package published on PyPI directly β no need to clone the source.
pip install dist/*.whl
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
3. Docker
Easy- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build -t codex-bridge .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 codex-bridge
Runs the built image as an actual container.
4. Python
Easypip install codex-bridge
Installs the package published on PyPI directly β no need to clone the source.
pip install dist/*.whl
Installs the package published on PyPI directly β no need to clone the source.
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
claude mcp add codex-bridge-dev -s user -- python -m src
Runs the Python script (or module).
python -m src
Runs the Python script (or module).
Pulled directly from this repo's README.