Codex BridgeSAFE
A lightweight MCP server bridging AI agents to OpenAI models via official CLI
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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>=2,<3and Codex CLI - Easy Deployment: Support for both uvx and traditional pip installation
- Universal MCP Compatibility: Works with any MCP-compatible AI coding assistant
🚀 Quick Start
Prerequisites
- Install Codex CLI:
npm install -g @openai/codex-cli
- Authenticate with Codex:
codex
- Verify installation:
codex --version
Installation
🎯 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
e468775911cfOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add codex-bridge -- uvx codex-bridge
{
"mcpServers": {
"codex-bridge": {
"command": "uvx",
"args": [
"codex-bridge"
]
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
consult_codex | read | |
consult_codex_batch | read | |
consult_codex_with_stdin | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
e468775911cffull audit observations/trust-audit/mcp-server/elyin__codex-bridge.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | e468775911cf | SAFE | B | 89 | first audit |
Questions
What is the Codex Bridge MCP server?
A lightweight MCP server bridging AI agents to OpenAI models via official CLI
What tools does Codex Bridge expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Codex Bridge safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Codex Bridge need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (e468775911cf), read on 2026-10-07. The repository is watched and re-audited when it changes.