Run codex agents --no-daemon to open a command center that marks unread results, and switch between connected backends from the session picker with your drafts kept. It also previews local image attachments and adds an optional Vertex AI setup wizard behind gcp_setup_wizard.
Announced Nov 10, it installs npm and Python packages, CLIs and remote URLs as MCP servers through one interface, and checks that each works before an agent uses it. API tokens go in the system keychain instead of config files; it's MIT licensed and runs on macOS and Linux…
Launched Nov 10, you paste one line into your agent, sign in with OAuth (no API key), and it deploys, reads logs and rolls back. Billing is per minute from prepaid wallet credit ($5/mo Personal, $20/mo Team), with a monthly cap that pauses apps…
The remote server signs in with OAuth (no API key) and lets your assistant search launches, compare alternatives, read reviews and check leaderboards. It can also draft and schedule your launch, but submitting or editing starts with a preview that waits for your confirmation…
Announced Nov 10, the server is available on every Zapnito tier and lets Claude, ChatGPT or any MCP client query a community's live discussions, content and expert answers. Zapnito's docs say it is read only…
Announced Nov 10, it connects with one link and a PrimeXBT login, with read only and read and trade permissions. Every order needs explicit confirmation, and the MCP can't withdraw or transfer funds…
Spotted something we missed? Start a thread.