TL;DR. Fastest path: install the Hatchable plugin. Run /plugins in the Codex CLI (or open Plugins in the Codex app), install Hatchable, approve the sign-in. Manual route: add [mcp_servers.hatchable] with url = "https://hatchable.com/mcp" to ~/.codex/config.toml, then run codex mcp login hatchable. Either way, OAuth signs you in and creates the free account.

What is an MCP server in Codex?

OpenAI Codex is an AI coding agent with a desktop app, CLI, and IDE extension. It supports the Model Context Protocol (MCP), which lets it call external tools (databases, APIs, deployment targets) as first-class functions during a session. Registering an MCP server in Codex adds a new tool category to what Codex can do without any new model training. Codex also has a plugin directory: a plugin bundles an MCP server plus its setup, so installing one replaces the manual configuration entirely.

Hatchable's MCP server exposes tools for creating projects, deploying code, and querying the app's database, so Codex can take you from "describe the app" to "live URL" in one session.

The fast path: install the Hatchable plugin

Hatchable is a listed ChatGPT app, and OpenAI distributes listed apps to Codex as plugins. Installing the plugin does everything the manual steps below do:

  1. Open the plugin directory

    In the Codex app, open the Plugins section. In the Codex CLI, run /plugins to open the plugin browser.

  2. Install Hatchable

    Search for Hatchable, open it, and select Install.

  3. Authenticate

    Approve the sign-in tab that opens on hatchable.com. If this is your first visit, approving also creates your free Hatchable account. No email step, no credit card.

  4. Try it

    Start a new thread and ask Codex to do something that requires the server (or type @ and pick Hatchable to invoke it explicitly):

    "Build a small habit-tracker web app on Hatchable. Make it for personal use."

    Codex will propose a plan, ask for permission, then call Hatchable's tools to create the project, write the files, and deploy it. You'll get a live URL back in the same session.

The manual route: config.toml

Prefer to wire up the MCP server yourself, or on a locked-down setup where the plugin directory isn't available? Codex reads MCP servers from ~/.codex/config.toml (a project-scoped .codex/config.toml works too). The whole entry is two lines:

[mcp_servers.hatchable]
url = "https://hatchable.com/mcp"

Remote servers use the Streamable HTTP transport automatically when you give a url. No bearer token, header, or environment variable is needed. Then authenticate:

codex mcp login hatchable

A browser tab opens on hatchable.com. Approve, and Codex stores the OAuth credentials for future sessions. In the IDE extension, the same file is reachable from the gear menu via MCP settings → Open config.toml.

Why OAuth over a bearer token? OAuth credentials are scoped per-client, rotate transparently, and can't leak out of Codex the way a shell env var can. Codex still supports bearer tokens via the bearer_token_env_var config key for MCP servers that don't speak OAuth — Hatchable does, so you skip that.

Removing or updating the server

Installed the plugin? Remove or disable it from the same Plugins section (or /plugins browser) you installed it from. Configured it manually? Delete the [mcp_servers.hatchable] block from config.toml. If OAuth ever falls out of sync — say you revoked Codex's access from your Hatchable account — run codex mcp login hatchable again (or re-authenticate the plugin) to re-link.

Troubleshooting

"Tool not available" or Codex doesn't list Hatchable tools

Walk through these in order:

Sign-in does nothing, or the browser tab hangs

Codex runs in the cloud — does OAuth still work?

Yes. Codex's cloud execution mode reuses the OAuth credentials stored when you authenticated locally. They ride along with the session, authenticate the MCP calls from the cloud runner, and aren't logged on OpenAI's side.

Deploy Codex-built apps to a live URL, free.

Hatchable hosts everything your AI builds. Free forever — bring your own AI.

Get started free →

Frequently asked questions

Is Codex's MCP support the same as Claude Code's?

The protocol is the same — any server that speaks MCP works in both. The setup flow differs: Claude Code uses a claude mcp add CLI command, while Codex installs plugins from its directory or reads ~/.codex/config.toml. Servers are interchangeable; only the client config differs.

Do I need an OpenAI account separately from my Hatchable account?

Yes. Your OpenAI account authenticates Codex to OpenAI's models. Your Hatchable account (created automatically the first time you approve the sign-in) authorizes Codex's MCP calls to Hatchable. They're separate services and separate logins.

Can I use multiple MCP servers in Codex at once?

Yes — install more plugins, or add one [mcp_servers.name] block per server. Codex surfaces every enabled server's tools to the model in the same session, so you can mix Hatchable with other MCP-speaking services like databases, issue trackers, or browser automation.

Does Codex work with the free OpenAI tier?

The Codex app itself is free. You need an OpenAI account with model access for the calls Codex makes. Most Hatchable users on Codex spend a few cents per project because tool-heavy sessions are short.

What if my Codex version doesn't have a Plugins section?

Plugin support ships in recent builds. Update Codex from openai.com/codex, or skip the directory entirely: the config.toml route above works on any current Codex build.