Relays coding work from ChatGPT to a local Codex CLI session over an OpenAI tunnel, using the user's ChatGPT sign-in and Codex plan limits. Checks five-hour and weekly Codex quota before each request, records Codex request IDs so unchanged resends return the original task, and returns changed files and command output as evidence for ChatGPT to review.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ThriftyRelay Add a new API endpoint to handle user profile updates and write unit tests for it."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ThriftyRelay is a local MCP server that lets ChatGPT hand coding work to Codex on your own machine. Codex uses your ChatGPT sign-in and your plan's Codex limits, without separate API billing.
日本語 | English
ThriftyRelay is maintained by Roseu and is not affiliated with OpenAI. The npm package is not published; install it from a clone as shown below. Before 1.0, a minor release may include breaking changes; check the changelog before updating.
Checks five-hour and weekly limits before each new request. By default, ChatGPT asks for approval when either remaining limit falls to or below its threshold.
Records Codex request IDs. An unchanged resend returns the original task.
Retains unknown write outcomes for review and recovery.
ChatGPT plans the work and calls ThriftyRelay's MCP tools through an OpenAI tunnel.
tunnel-client on your machine passes each call to the local ThriftyRelay server.
ThriftyRelay checks admission, and the quota limits for Codex work, then runs the step: Codex for coding work, or a direct file read or command.
ThriftyRelay records the request and returns the changed files and command output.
ChatGPT reviews that evidence and decides whether the work is done.
Related MCP server: ChatGPT Codex Bridge
Node.js 22 or later, npm, and Git
A Codex CLI sign-in with a ChatGPT account
An OpenAI tunnel ID, a tunnel API key for that tunnel, and a tunnel-client executable
Linux: secret-tool with a Secret Service session and ss
macOS: the login Keychain and lsof
Setup covers where to get each item and how to choose a workspace. Platform status shows what has been tested on each system.
git clone https://github.com/Roseu7/Thrifty-Relay.git
cd Thrifty-Relay
npm ci
npm install -g .npm install -g . links the thriftyrelay command to this clone, so keep the clone where it is.
npm may warn that the thrifty-relay install script was not allowed; npm ci has already run it.
Run setup from the directory you want Codex to work in; setup offers it as the workspace.
thriftyrelay setupOn an existing Windows installation, setup can stop and replace the running task, so check for running work first as described in operations.
thriftyrelay setup
thriftyrelay startLinux and macOS setup saves the configuration and does not start anything; start runs it in the background, and thriftyrelay stop stops it.
Setup explains the startup modes and what setup verifies.
Keep ThriftyRelay running, then add it to ChatGPT on the web:
Open ChatGPT Plugins, select the plus button, then Add custom MCP server.
Enter ThriftyRelay as the name.
Under Connection, select Tunnel and choose your tunnel, then select No authentication.
Confirm the risk warning, select Create as a plugin, and install the plugin.
Setup covers each step, plan and workspace permissions, and what to check if the tunnel does not appear.
Start a new conversation, type @, select ThriftyRelay, and ask it to call health.
A healthy reply looks like this:
ThriftyRelay <version>: OK; Windows; file/shell tools available (26 internal tools); build=<build>; source=current; codex=target-configured; writers=coordinated; scratch=configured; enforcement=unregisteredResponse | Meaning or next step |
Starts with | ChatGPT reached the server. |
| A Codex workspace is configured. Try the small task below to check execution. |
| Configure a Codex workspace with setup. |
| Source files changed after startup. Follow the restart procedure before sending work. |
Then give Codex a small task that does not change anything, for example: ask Codex to list the files in the workspace and explain what the project does.
Without a registeredadmission policy, Codex uses danger-full-access under the account running ThriftyRelay.
The policy selects the Codex worker's sandbox.
Working-directory and write-scope checks control request admission; the worker sandbox controls filesystem access. If a write ends with an unknown outcome, follow recovery instead of resending it.
The startup catalog lists global Codex Skills from ~/.codex/skills.
See Skills for selection, disabling entries with enabled = false, and handling their contents as untrusted data within the existing permissions.
Goal | Guide |
Install and connect | |
Start, stop, update, or uninstall | |
Choose models and quota actions | |
Submit and review Codex work | |
Use global Skills | |
Configure access and write scopes | |
Investigate an unknown execution | |
Understand implementation and contribute |
npm ci, node scripts/check-syntax.mjs, and npm test run the offline checks.
CONTRIBUTING.md lists the per-area test commands.
Bug reports, documentation fixes, and focused changes are welcome. Report vulnerabilities privately as described in SECURITY.md, and see CHANGELOG.md for changes.
MIT License. Dependency licenses are in THIRD_PARTY_NOTICES.md.
This server cannot be deployed
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
Work on your own computers from Claude or ChatGPT: run commands, edit and search files.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log
