Codex

Go-based MCP server that wraps the Codex CLI to enable multi-client workflows with session management and sandboxing.
  • go

31

GitHub Stars

go

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "w31r4-codex-mcp-go": {
      "command": "npx",
      "args": [
        "-y",
        "@zenfun510/codex-mcp-go"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run Codex MCP Server to expose the Codex CLI as an MCP tool, enabling multi-client sessions, sandboxed execution, and concurrent usage. This server wraps the Codex CLI so clients like Claude Code, Roo Code, and KiloCode can invoke it through MCP for complex coding tasks.

How to use

You connect to the Codex MCP Server from your MCP-capable client. Start a session to perform multi-turn interactions, then issue commands through the MCP interface to generate, analyze, or modify code using Codex.

How to install

Prerequisites: you need Node.js and npm, plus Go if you plan to build from source. You also must have the Codex CLI installed and configured to access OpenAI APIs.

# Install Codex CLI (recommended)
npm i -g @openai/codex

# Start MCP server using npx (recommended method)
npx @zenfun510/codex-mcp-go

# Or, build from source (requires Go 1.24+)
# 1) Clone the repository
# git clone https://github.com/w31r4/codex-mcp-go.git
# 2) Build the binary
# cd codex-mcp-go
# go build -o codex-mcp-go cmd/server/main.go

# Run the built binary directly
./codex-mcp-go

Additional setup and configuration

Configure your MCP client to use either the local binary or the npx-wrapped command. Examples show both approaches with the required environment variables.

Available tools

codex

Codex MCP tool wrapper that executes Codex CLI tasks under MCP protocol, enabling code generation, debugging, and multi-turn sessions.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational