eLyiN/codex-bridge
If you are the rightful owner of codex-bridge and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Codex Bridge is a lightweight MCP server that facilitates interaction between AI coding assistants and OpenAI's Codex AI using the official CLI.
Codex Bridge
A lightweight MCP (Model Context Protocol) server that enables AI coding assistants to interact with OpenAI's Codex AI through the official CLI. Works with Claude Code, Cursor, VS Code, and other MCP-compatible clients. Designed for simplicity, reliability, and seamless integration.
⨠Features
- Direct Codex CLI Integration: Zero API costs using official Codex CLI
- Simple MCP Tools: Two core functions for basic queries and file analysis
- Stateless Operation: No sessions, caching, or complex state management
- Production Ready: Robust error handling with configurable timeouts (default: 90 seconds)
- Minimal Dependencies: Only requires
mcp>=1.0.0
and Codex CLI - Easy Deployment: Support for both uvx and traditional pip installation
- Universal MCP Compatibility: Works with any MCP-compatible AI coding assistant
š Quick Start
Prerequisites
-
Install Codex CLI:
npm install -g @openai/codex-cli
-
Authenticate with Codex:
codex
-
Verify installation:
codex --version
Installation
šÆ Recommended: PyPI Installation
# Install from PyPI
pip install codex-bridge
# Add to Claude Code with uvx (recommended)
claude mcp add codex-bridge -s user -- uvx codex-bridge
Alternative: From Source
# Clone the repository
git clone https://github.com/shelakh/codex-bridge.git
cd codex-bridge
# Build and install locally
uvx --from build pyproject-build
pip install dist/*.whl
# Add to Claude Code
claude mcp add codex-bridge -s user -- uvx codex-bridge
Development Installation
# Clone and install in development mode
git clone https://github.com/shelakh/codex-bridge.git
cd codex-bridge
pip install -e .
# Add to Claude Code (development)
claude mcp add codex-bridge-dev -s user -- python -m src
š Multi-Client Support
Codex Bridge works with any MCP-compatible AI coding assistant - the same server supports multiple clients through different configuration methods.
Supported MCP Clients
- Claude Code ā (Default)
- Cursor ā
- VS Code ā
- Windsurf ā
- Cline ā
- Void ā
- Cherry Studio ā
- Augment ā
- Roo Code ā
- Zencoder ā
- Any MCP-compatible client ā
Configuration Examples
Claude Code (Default)
# Recommended installation
claude mcp add codex-bridge -s user -- uvx codex-bridge
# Development installation
claude mcp add codex-bridge-dev -s user -- python -m src
Cursor
Global Configuration (~/.cursor/mcp.json
):
{
"mcpServers": {
"codex-bridge": {
"command": "uvx",
"args": ["codex-bridge"],
"env": {}
}
}
}
Project-Specific (.cursor/mcp.json
in your project):
{
"mcpServers": {
"codex-bridge": {
"command": "uvx",
"args": ["codex-bridge"],
"env": {}
}
}
}
Go to: Settings
ā Cursor Settings
ā MCP
ā Add new global MCP server
VS Code
Configuration (.vscode/mcp.json
in your workspace):
{
"servers": {
"codex-bridge": {
"type": "stdio",
"command": "uvx",
"args": ["codex-bridge"]
}
}
}
Alternative: Through Extensions
- Open Extensions view (Ctrl+Shift+X)
- Search for MCP extensions
- Add custom server with command:
uvx codex-bridge
Windsurf
Add to your Windsurf MCP configuration:
{
"mcpServers": {
"codex-bridge": {
"command": "uvx",
"args": ["codex-bridge"],
"env": {}
}
}
}
Cline (VS Code Extension)
- Open Cline and click MCP Servers in the top navigation
- Select Installed tab ā Advanced MCP Settings
- Add to
cline_mcp_settings.json
:
{
"mcpServers": {
"codex-bridge": {
"command": "uvx",
"args": ["codex-bridge"],
"env": {}
}
}
}
Void
Go to: Settings
ā MCP
ā Add MCP Server
{
"mcpServers": {
"codex-bridge": {
"command": "uvx",
"args": ["codex-bridge"],
"env": {}
}
}
}
Cherry Studio
- Navigate to Settings ā MCP Servers ā Add Server
- Fill in the server details:
- Name:
codex-bridge
- Type:
STDIO
- Command:
uvx
- Arguments:
["codex-bridge"]
- Name:
- Save the configuration
Augment
Using the UI:
- Click hamburger menu ā Settings ā Tools
- Click + Add MCP button
- Enter command:
uvx codex-bridge
- Name: Codex Bridge
Manual Configuration:
"augment.advanced": {
"mcpServers": [
{
"name": "codex-bridge",
"command": "uvx",
"args": ["codex-bridge"],
"env": {}
}
]
}
Roo Code
- Go to Settings ā MCP Servers ā Edit Global Config
- Add to
mcp_settings.json
:
{
"mcpServers": {
"codex-bridge": {
"command": "uvx",
"args": ["codex-bridge"],
"env": {}
}
}
}
Zencoder
- Go to Zencoder menu (...) ā Tools ā Add Custom MCP
- Add configuration:
{
"command": "uvx",
"args": ["codex-bridge"],
"env": {}
}
- Hit the Install button
Alternative Installation Methods
For pip-based installations:
{
"command": "codex-bridge",
"args": [],
"env": {}
}
For development/local testing:
{
"command": "python",
"args": ["-m", "src"],
"env": {},
"cwd": "/path/to/codex-bridge"
}
For npm-style installation (if needed):
{
"command": "npx",
"args": ["codex-bridge"],
"env": {}
}
Universal Usage
Once configured with any client, use the same two tools:
- Ask general questions: "What authentication patterns are used in this codebase?"
- Analyze specific files: "Review these auth files for security issues"
The server implementation is identical - only the client configuration differs!
āļø Configuration
Timeout Configuration
By default, Codex Bridge uses a 90-second timeout for all CLI operations. For longer queries (large files, complex analysis), you can configure a custom timeout using the CODEX_TIMEOUT
environment variable.
Git Repository Check
By default, Codex CLI requires being inside a Git repository or trusted directory. If you need to use Codex Bridge in directories that aren't Git repositories, you can set the CODEX_SKIP_GIT_CHECK
environment variable.
ā ļø Security Warning: Only enable this flag in trusted environments where you control the directory structure.
Example configurations:
Claude Code
# Add with custom timeout (120 seconds)
claude mcp add codex-bridge -s user --env CODEX_TIMEOUT=120 -- uvx codex-bridge
# Add with git repository check disabled (for non-git directories)
claude mcp add codex-bridge -s user --env CODEX_SKIP_GIT_CHECK=true -- uvx codex-bridge
# Add with both configurations
claude mcp add codex-bridge -s user --env CODEX_TIMEOUT=120 --env CODEX_SKIP_GIT_CHECK=true -- uvx codex-bridge
Manual Configuration (mcp_settings.json)
{
"mcpServers": {
"codex-bridge": {
"command": "uvx",
"args": ["codex-bridge"],
"env": {
"CODEX_TIMEOUT": "120",
"CODEX_SKIP_GIT_CHECK": "true"
}
}
}
}
Configuration Options:
CODEX_TIMEOUT:
- Default: 90 seconds (if not configured)
- Range: Any positive integer (seconds)
- Recommended: 60-120 seconds for most queries, 120-300 for large file analysis
- Invalid values: Fall back to 90 seconds with warning
CODEX_SKIP_GIT_CHECK:
- Default: false (Git repository check enabled)
- Valid values: "true", "1", "yes" (case-insensitive) to disable the check
- Use case: Working in directories that are not Git repositories
- Security: Only use in trusted directories you control
š ļø Available Tools
consult_codex
Direct CLI bridge for simple queries with structured JSON output by default.
Parameters:
query
(string): The question or prompt to send to Codexdirectory
(string): Working directory for the query (default: current directory)format
(string): Output format - "text", "json", or "code" (default: "json")timeout
(int, optional): Timeout in seconds (recommended: 60-120, default: 90)
Example:
consult_codex(
query="Find authentication patterns in this codebase",
directory="/path/to/project",
format="json", # Default format
timeout=90 # Default timeout
)
consult_codex_with_stdin
CLI bridge with stdin content for pipeline-friendly execution.
Parameters:
stdin_content
(string): Content to pipe as stdin (file contents, diffs, logs)prompt
(string): The prompt to process the stdin contentdirectory
(string): Working directory for the queryformat
(string): Output format - "text", "json", or "code" (default: "json")timeout
(int, optional): Timeout in seconds (recommended: 60-120, default: 90)
consult_codex_batch
Batch processing for multiple queries - perfect for CI/CD automation.
Parameters:
queries
(list): List of query dictionaries with 'query' and optional 'timeout'directory
(string): Working directory for all queriesformat
(string): Output format - currently only "json" supported for batch
Example:
consult_codex_with_stdin(
stdin_content=open("src/auth.py").read(),
prompt="Analyze this auth file and suggest improvements",
directory="/path/to/project",
format="json", # Default format
timeout=120 # Custom timeout for complex analysis
)
š Usage Examples
Basic Code Analysis
# Simple research query
consult_codex(
query="What authentication patterns are used in this project?",
directory="/Users/dev/my-project"
)
Detailed File Review
# Analyze specific files
with open("/Users/dev/my-project/src/auth.py") as f:
auth_content = f.read()
consult_codex_with_stdin(
stdin_content=auth_content,
prompt="Review this file and suggest security improvements",
directory="/Users/dev/my-project",
format="json", # Structured output
timeout=120 # Allow more time for detailed analysis
)
Batch Processing
# Process multiple queries at once
consult_codex_batch(
queries=[
{"query": "Analyze authentication patterns", "timeout": 60},
{"query": "Review database implementations", "timeout": 90},
{"query": "Check security vulnerabilities", "timeout": 120}
],
directory="/Users/dev/my-project",
format="json" # Always JSON for batch processing
)
šļø Architecture
Core Design
- CLI-First: Direct subprocess calls to
codex
command - Stateless: Each tool call is independent with no session state
- Configurable Timeout: 90-second default execution time (configurable)
- Structured Output: JSON format by default for better integration
- Simple Error Handling: Clear error messages with fail-fast approach
Project Structure
codex-bridge/
āāā src/
ā āāā __init__.py # Entry point
ā āāā __main__.py # Module execution entry point
ā āāā mcp_server.py # Main MCP server implementation
āāā .github/ # GitHub templates and workflows
āāā pyproject.toml # Python package configuration
āāā README.md # This file
āāā CONTRIBUTING.md # Contribution guidelines
āāā CODE_OF_CONDUCT.md # Community standards
āāā SECURITY.md # Security policies
āāā CHANGELOG.md # Version history
āāā LICENSE # MIT license
š§ Development
Local Testing
# Install in development mode
pip install -e .
# Run directly
python -m src
# Test CLI availability
codex --version
Integration with Claude Code
The server automatically integrates with Claude Code when properly configured through the MCP protocol.
š Troubleshooting
CLI Not Available
# Install Codex CLI
npm install -g @openai/codex-cli
# Authenticate
codex auth login
# Test
codex --version
Connection Issues
- Verify Codex CLI is properly authenticated
- Check network connectivity
- Ensure Claude Code MCP configuration is correct
- Check that the
codex
command is in your PATH
Common Error Messages
- "CLI not available": Codex CLI is not installed or not in PATH
- "Authentication required": Run
codex auth login
- "Timeout after X seconds": Query took too long, try increasing timeout or breaking into smaller parts
š¤ Contributing
We welcome contributions from the community! Please read our for details on how to get started.
Quick Contributing Guide
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
š License
This project is licensed under the MIT License - see the file for details.
š Version History
See for detailed version history.
š Support
- Issues: Report bugs or request features via GitHub Issues
- Discussions: Join the community discussion
- Documentation: Additional docs can be created in the
docs/
directory
Focus: A simple, reliable bridge between Claude Code and Codex AI through the official CLI.