codex-gemini-bridge
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@codex-gemini-bridge Use Gemini to review this pull request"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
codex-gemini-bridge
A lightweight, zero-dependency MCP server that connects OpenAI Codex to Gemini models via your local Antigravity CLI (agy).
Supports macOS, Linux, and Windows.
1. Prerequisites
Node.js:
>= 22.0.0(node --version)Antigravity CLI (
agy):Install
agyfrom the official installation guide.Authenticate with Google:
agy auth login agy models
Related MCP server: codex-cli-mcp-tool
2. Quick Install & Auto-Config (Recommended)
Run the one-liner setup command for your operating system. It downloads the project to ~/.codex/mcp-servers/codex-gemini-bridge and automatically configures Codex (~/.codex/config.toml):
macOS / Linux
bash <(curl -fsSL https://raw.githubusercontent.com/theotherkim/codex-gemini-bridge/main/scripts/setup.sh)Windows (PowerShell)
irm https://raw.githubusercontent.com/theotherkim/codex-gemini-bridge/main/scripts/setup.ps1 | iex(If you already cloned the repo locally, simply run npm run setup inside the project directory).
3. Manual Configuration (Optional)
If you prefer to configure manually, clone the repository into your Codex MCP directory:
macOS / Linux
git clone https://github.com/theotherkim/codex-gemini-bridge.git ~/.codex/mcp-servers/codex-gemini-bridgeAdd to ~/.codex/config.toml:
[mcp_servers.codex-gemini-bridge]
command = "node"
args = ["~/.codex/mcp-servers/codex-gemini-bridge/src/index.mjs"]
env_vars = ["AGY_BIN"](Or via Codex CLI: codex mcp add codex-gemini-bridge -- node ~/.codex/mcp-servers/codex-gemini-bridge/src/index.mjs)
Windows
git clone https://github.com/theotherkim/codex-gemini-bridge.git "$env:USERPROFILE\.codex\mcp-servers\codex-gemini-bridge"Add to %USERPROFILE%\.codex\config.toml:
[mcp_servers.codex-gemini-bridge]
command = "node"
args = ["C:/Users/<YourUsername>/.codex/mcp-servers/codex-gemini-bridge/src/index.mjs"]
env_vars = ["AGY_BIN"]4. Usage
Restart Codex, then ask in natural language:
"Ask Gemini to summarize this codebase"
"Use Gemini to review this pull request"
"List available models with
gemini_models"
Available Tools
gemini: Send prompts to Gemini (supportsprompt,model,thinking_level,store, etc.).gemini_models: List all models available to your local account.
License
MIT © Kim
Available Tools
2 toolsgeminiA
Send a prompt to the local Antigravity CLI and return the model text output. The default model is Gemini 3.7 Flash High. Pass store=true to receive a conversation_id that can be used with previous_interaction_id on a later call. Returns model text, interaction_id, model, usage metadata and status. Never returns credentials.
Inputs: prompt (required), model, store, timeout_ms, +3 more.
gemini_modelsA
List the models available to the local Antigravity CLI. Returns filtered model ids and display names.
Inputs: filter.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: 'gemini' sends prompts and returns text completions, while 'gemini_models' lists available models. There is no ambiguity or overlap between them.
Both names share the 'gemini' prefix, but one is a bare noun and the other uses an underscore suffix. This is readable and predictable, though it doesn't follow a strict verb_noun pattern.
With only two tools, the server feels extremely thin for a general bridge. However, the scope is limited to prompt execution and model listing, so the count is borderline acceptable.
The core functions of sending prompts and listing models are covered, including support for conversation history via IDs. Minor gaps exist, such as streaming or explicit model selection parameters in the main tool, but the essential workflow is usable.
Maintenance
Related MCP Connectors
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server for AI dialogue using various LLM models via AceDataCloud
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
An MCP server that gives your AI access to the source code and docs of all public github repos
Related MCP Servers
- AlicenseAqualityFmaintenanceA lightweight MCP server that enables AI coding assistants to interact with Google's Gemini AI through the official CLI.3MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that allows Claude Code to interact with the OpenAI Codex CLI.40 npm20MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that integrates Google Gemini CLI with Claude Code for AI-powered development assistance, enabling code review, bug analysis, feature planning, and code explanation without requiring an API key.8MIT
- FlicenseNot gradedqualityCmaintenanceAn MCP server that leverages Google Antigravity SDK and Gemini Enterprise Agent Platform to provide AI-driven code review and task execution via natural language.1-