OpenAI Codex CLI MCP

The Aikido MCP Plugin connects Aikido’s security engine to AI coding tools. It automatically scans AI generated code for vulnerabilities and hardcoded secrets as soon as it is created.

AI assistants can review their own output, but that review is not perfect. Aikido adds a reliable and consistent security layer that checks every generated snippet with proven scanning rules.

Why use Aikido MCP

• Deterministic, independent security checks on every AI generated snippet before it is committed

• Immediate detection and remediation of vulnerabilities and hardcoded secrets in AI assisted workflows

• Real time feedback, making AI driven development safer by default

For the full list of tools the MCP server exposes, see Available tools.

Installation

1

Install the Aikido MCP server

codex mcp add aikido -- npx -y @aikidosec/mcp@latest

2

Authenticate

On first use, the MCP server will detect no authentication is set. Ask Codex to run aikido_login. It will return a browser link. Follow the link to log in to Aikido. Your token is stored securely once login is complete.

3

Add the Aikido rule to Global AGENTS file

Create the codex directory if it doesn't exist yet.

mkdir -p ~/.codex/skills

Download the Aikido rule and add it to ~/.codex/skills/aikido-rule.txt.

curl -fsSL "https://gist.githubusercontent.com/kidk/aa48cad6db80ba4a38493016aae67712/raw/3644397b7df43423e3da06434491b40bbb79dd47/aikido-rule.txt" \
  -o ~/.codex/skills/aikido-rule.txt

4

Finished

Aikido MCP is now available in Codex CLI.

Restart Codex CLI if it was open.

For CI/CD or headless setups where browser login is not possible, see Token Authentication.

For ways to ask your agent to use Aikido, see Example prompts.