chatgpt_bridge
Automates ChatGPT through the chatgpt.com web UI using a user's own ChatGPT subscription. Supports sending prompts and local files, selecting GPT-6 power levels or Deep research, waiting for long-running jobs in the background, following up in the same chat, and fetching answers as clean Markdown with preserved formatting and citations.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
chatgpt-bridge
English · 한국어
Ask ChatGPT (GPT-6 Pro, Deep research) from Claude Code or Codex: send a prompt and local files to chatgpt.com, keep working while it thinks for 5–30 minutes, and get the answer back as a Markdown file. It works through your own ChatGPT subscription in a dedicated Chrome window, so no API key is needed.
This is an unofficial tool, not made by or affiliated with OpenAI or Anthropic. It automates the chatgpt.com web UI with your own account.
Terms of use: automating the ChatGPT UI may conflict with OpenAI's terms, and your account is at your own risk.
Breakage: it can stop working whenever ChatGPT's UI changes. See When ChatGPT's UI changes.
Uploads: files you attach are uploaded to OpenAI.
What it does
Pick the model. It moves the GPT-6 power slider (Instant · Medium · High · Extra High · Pro), turns on Deep research, or picks a model version.
Upload files. It attaches local files and checks that ChatGPT received them before sending.
Wait in the background. A job is a ChatGPT conversation. It survives your agent session ending, and Claude Code, Codex and the CLI all share it.
Save clean Markdown.
Normal answers are copied with ChatGPT's own Copy button, so code blocks, tables, math and links stay intact. Your clipboard is never touched.
Deep research reports are read from the research app's own state. Their citations become numbered links plus a
## Sourceslist.
Stay safe. It never types your password and never bypasses Cloudflare or other browser checks; it asks you to handle them.
Example output: a Pro answer and a Deep research report.
Related MCP server: local-agent-mcp
Requirements
macOS, Linux or Windows with Google Chrome or Chromium. macOS is the most tested.
Node.js 22+ with
npmon thePATHof Claude Code / Codex.A ChatGPT account. Pro needs a Pro, Business or Enterprise plan; see plan limits.
Install
Claude Code
/plugin marketplace add leeheewon-01/chatgpt-bridge
/plugin install chatgpt-bridge@chatgpt-bridgeFrom a shell, the same two steps are:
claude plugin marketplace add leeheewon-01/chatgpt-bridge
claude plugin install chatgpt-bridge@chatgpt-bridgeStart a new session. /mcp should list plugin:chatgpt-bridge:chatgpt_bridge as connected.
Codex (CLI or the ChatGPT desktop app)
codex plugin marketplace add leeheewon-01/chatgpt-bridge
codex plugin add chatgpt-bridge@chatgpt-bridgeRestart Codex. The first start installs the npm dependencies into the plugin folder, which takes about a minute. Codex allows 180 s for that.
From a clone
git clone https://github.com/leeheewon-01/chatgpt-bridge.git
cd chatgpt-bridge
npm ci
node scripts/install.mjs # or: node scripts/install.mjs claude | codexThis registers the clone as a local marketplace in both tools.
Claude Code loads it in place, so your edits apply in the next session.
Codex copies it, so re-run the script after editing.
First run: sign in once
Ask your agent to check the ChatGPT session, or run the CLI:
node <plugin folder>/src/cli.js loginA Chrome window opens on chatgpt.com. Sign in there yourself. The session is kept in its own profile at ~/.chatgpt-bridge/profile, separate from your everyday Chrome. The bridge never sees your password.
Why a separate Chrome? Since Chrome 136, remote debugging is ignored on the default profile. A dedicated profile also keeps the agent away from your other tabs and accounts.
Usage
Just ask your agent, for example:
"Send
spec.mdto GPT Pro and ask for the weakest parts of the design. Save the answer under research/.""Run ChatGPT Deep research on the current state of solid-state batteries."
"Ask ChatGPT for a second opinion on this diff."
The bundled skill picks the right tools.
Submit:
chatgpt_submitstarts the job.Wait: Claude Code waits with a background CLI and is notified when the job ends. Codex calls
chatgpt_wait.Save:
chatgpt_fetchwrites the Markdown file.
Tool | What it does |
| Start the Chrome window if needed; report login state and file locations |
| Bring the window to the front so you can sign in |
| New chat, then power level or Deep research, files and prompt; returns a |
| Current state / block until done (up to 25 min per call) |
| Follow-up in the same chat, e.g. to answer Deep research's questions |
| Save the answer as Markdown ( |
| Recent jobs / close a finished tab |
| Selector diagnostics for when the UI changes |
The mode argument of chatgpt_submit:
instant,medium,high,extra_high,pro: positions of the power slider.deep_research: Deep research.default: keeps whatever is selected.
The chosen level stays as your ChatGPT default for new chats. Set model_version (for example "GPT-5.6") to pick another entry of the version list.
A job_id is the ChatGPT conversation id, so a chatgpt.com/c/... URL works too.
CLI
node src/cli.js submit --mode pro --file ./spec.pdf "Find the weak points of this design"
node src/cli.js wait <job_id> --timeout 3600 --out ./research/review.md --notify
node src/cli.js status <job_id>
node src/cli.js jobsPlan limits
Every pro submit uses one GPT-6 Pro message, and every deep_research submit uses one Deep research task, from your plan's allowance. Snapshot from 2026-10-19:
Plan | GPT-6 Pro in Chat |
Free · Go · Plus | not included |
Pro 100 ($100) | 50 / week (archived official figure) |
Pro 200 ($200) | 200 / week (archived official figure); reported to drop to 100 / week from 2026-10-30 |
Pro 500 ($500) | highest of the Pro plans; count not published |
Business Standard / Premium | 15 / month · 50 / week |
Enterprise · Edu | credits: 50 per GPT-6 Pro message |
OpenAI doesn't publish Deep research counts for most plans. Details, sources and caveats are in docs/plan-limits.md.
How it works
Claude Code ─┐ ┌─ dedicated Chrome (~/.chatgpt-bridge/profile)
Codex ───────┼─ MCP server / CLI ─ CDP ─┤ chatgpt.com tabs, one per job
CLI ─────────┘ (src/bridge.js) └─ Deep research app iframe (read over raw CDP)Shared Chrome: every bridge process connects to one Chrome over the DevTools protocol on
127.0.0.1:9339. A launch lock prevents two windows from starting.Selectors:
selectors.jsonholds everything the bridge knows about ChatGPT's page. It is re-read on every call.Completion check: an answer is complete when the stop button is gone and the reply's action-bar Copy button appears.
Deep research: it runs inside a sandboxed app iframe. The bridge reads that app's
window.openai.widgetState(plan, status, report) and nothing else from it.State files: jobs live in
~/.chatgpt-bridge/jobs.json, and every fetched answer is also copied to~/.chatgpt-bridge/results/<job_id>.md.
File | Role |
| MCP server (stdio) |
| The same features as a CLI |
| Submit, status, wait and fetch logic |
| Code that runs inside the page: element lookup, completion check, extraction |
| Deep research state and citations, raw CDP into its iframe |
| Plugin entry point; installs dependencies on the first start |
When ChatGPT's UI changes
Errors tagged [selector] or [model] mean the page no longer matches. Run chatgpt_inspect (or node src/cli.js inspect). In its matches list, entries that print NO MATCH are the ones to fix.
Put corrected entries in ~/.chatgpt-bridge/selectors.json. Its top-level keys replace the bundled ones, it is re-read on every call, and it survives plugin updates. For example:
{ "stopButton": ["button[aria-label*='Stop']", "button[data-testid='stop-button']"] }Pull requests that update selectors.json are very welcome.
Configuration
Variable | Default | |
|
| profile, jobs, results, selector override |
|
| Chrome remote-debugging port, bound to 127.0.0.1 |
| auto-detected | path to the Chrome or Chromium executable |
| bundled | replace the selector file entirely |
Update and uninstall
Claude Code:
Update:
claude plugin marketplace update chatgpt-bridge, thenclaude plugin update chatgpt-bridge@chatgpt-bridge.Uninstall:
claude plugin uninstall chatgpt-bridge@chatgpt-bridge.
Codex:
Update:
codex plugin marketplace upgrade chatgpt-bridge, thencodex plugin add chatgpt-bridge@chatgpt-bridge.Uninstall:
codex plugin remove chatgpt-bridge@chatgpt-bridge.
Your data: your login and results stay in
~/.chatgpt-bridge. Delete that folder to remove them.
Troubleshooting
needs_login: sign in in the bridge's Chrome window.chatgpt_loginbrings it to the front.challenge: ChatGPT is showing a browser check. Complete it in that window.The server doesn't start in Codex:
Codex must find
node(22+) andnpmon itsPATH. GUI apps sometimes get a shorterPATHthan your terminal.If the first-start install failed, run
npm ciin the plugin folder that the error names.
Chrome not found: setCHATGPT_BRIDGE_CHROMEto the full path of the Chrome executable.Tool names doubled: you have both an old manual MCP entry and the plugin. Remove the manual one (
claude mcp remove -s user chatgpt_bridge).The wrong power level is used:
active_modelin the submit result shows what ChatGPT selected. If Pro isn't available, your plan may not include it or this week's allowance may be used up.
Security and privacy
The debugging port: it listens on 127.0.0.1 only. Still, any program running as your user can drive the bridge's Chrome profile, so don't sign in to unrelated accounts in that window, and turn off Chrome sync there.
What leaves your computer: only what you send to ChatGPT. The bridge sends no telemetry.
ChatGPT's output: Deep research quotes web pages. The skill tells the agent to treat answers as data, not instructions.
Plugin code: a plugin runs with your user permissions, so read the code before you install it.
Development
npm ci
npm testThe tests drive a local fake ChatGPT page in a throwaway headless Chrome; they never contact chatgpt.com. They cover:
choosing the power level, attaching files, and submit → wait → copy-based extraction;
follow-ups in the same chat, and the fallback HTML extraction;
Deep research app state and citations;
logout detection and model-version errors.
License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
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.
Your own computer's files from ChatGPT or Claude: folder rules, confirmations and undo.
Your AI apps as one team: hand work to Codex or Claude Code on your Mac, with a shared logbook.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables Codex to delegate deep research, PRD drafting, design thinking, and current-information lookups to ChatGPT Web/App via a local MCP connector, saving Markdown results to the filesystem.MIT
- AlicenseBqualityCmaintenanceEnables ChatGPT to work directly on local projects by reading files, editing code, running tests and commands, inspecting Git state, and managing durable workflows, with optional delegation to local Codex agents for complex tasks.28MIT
- FlicenseAqualityDmaintenanceEnables web ChatGPT to drive durable, sandboxed Claude Code sessions on a local Mac, with controlled read, modify, verify, and recover operations via six session control tools.6-
- FlicenseNot gradedqualityAmaintenanceEnables ChatGPT to use reviewed local Codex-backed tools for project files, Git, bounded terminal commands, Chrome/Edge browsing, and live Excel/document control from normal Chat. It calls the Codex model explicitly only when a task actually needs it.-