Skip to main content

Behavry Integration — OpenAI Codex CLI

OpenAI Codex CLI supports MCP servers via both Streamable HTTP and stdio transports. Configuration lives in ~/.codex/config.yaml.

Prerequisites​

  • Behavry stack running (make dev or docker compose up)
  • Codex CLI installed
  • Python 3.11+

Quick Setup​

make setup

Manual Configuration​

Add to ~/.codex/config.yaml:

mcp_servers:
  behavry:
    transport: streamable-http
    url: http://localhost:8000/mcp/v1/
    headers:
      Authorization: "Bearer <behavry-jwt>"

stdio​

mcp_servers:
  behavry:
    transport: stdio
    command: behavry-mcp-stdio
    args:
      - --server-url
      - http://localhost:8000
    env:
      BEHAVRY_CLIENT_ID: "<client_id>"
      BEHAVRY_CLIENT_SECRET: "<client_secret>"

Use stdio when HTTP connectivity from Codex CLI is restricted.

Verify​

  1. Run codex in a project directory and invoke a tool
  2. Check http://localhost:5173 → Live Activity for the event

Token Refresh​

make tokens

For stdio transport, credentials are used to obtain fresh tokens automatically.