If you already use Codex for real work, switching between separate websites for research, coding, image generation, and video creation quickly breaks your workflow. GlobalGPT CLI brings these capabilities into Codex, allowing it to call GlobalGPT models and tools while continuing to manage your files, tasks, and next steps in the same workspace.
In this tutorial, you’ll learn how to use GlobalGPT CLI in Codex from a clean installation to a working multi-model workflow. We’ll install the official npm package using either Terminal or Codex, authorize a GlobalGPT account, enable the bundled Skills, connect the MCP server, and verify the setup. You’ll then use the integration for practical tasks including web research, coding, image generation, and video creation.
What GlobalGPT Adds to Codex
GlobalGPT CLI, the bundled Skills, and the MCP server are three parts of the same integration. The CLI supplies the commands, the Skills teach Codex when and how to use them, and MCP exposes GlobalGPT capabilities as callable tools.
GlobalGPT CLI
Provides account, chat, image, video, Skill, and MCP commands.
GlobalGPT Skills
Teach Codex how to handle chat, coding, image, and video tasks.
GlobalGPT MCP
Exposes chat and media functions that Codex can call directly.
You do not need to choose only one of the three. Install the CLI first, then add the Skills and MCP connection so Codex can use the same GlobalGPT account in different ways.
Requisitos previos
Before starting, make sure you have:
- Codex installed and working.
- Node.js and npm available on your computer.
- A GlobalGPT account with enough credits for the models you plan to use.
- A browser for the one-time authorization step.
The npm installation command is the same on macOS, Windows, and Linux. You can type it in your normal terminal or give the command to Codex.
Install GlobalGPT CLI
Choose either method below. Both install the same official GlobalGPT CLI package and lead to the same setup steps afterward.
Method 1: Install GlobalGPT CLI in Terminal
Open Terminal, PowerShell, or your preferred command-line application and run the official installation command:
npm i -g @glbgpt/cli
Wait for npm to finish. A successful installation ends without an npm error and reports the packages that were added.
Verify the installed CLI:
glbgpt --versionComprobación de éxito: In this test, the installed package was @glbgpt/cli@0.1.1 and the version command returned 0.1.1. Your version may be newer when you follow the guide.
Method 2: Ask Codex to Install GlobalGPT CLI
If you prefer to stay inside Codex, send this instruction:
Install the official GlobalGPT CLI with this command:
npm i -g @glbgpt/cli
After installation, verify the installed package version and confirm
that both glbgpt and globalgpt command entries are available.
Codex can run the npm command, inspect the installed package, and verify the command entries for you.
Method 2 complete: Both installation methods lead to the same shared setup below. Do not install the package twice.
Log In to GlobalGPT
Start the browser authorization flow:
glbgpt loginYou can also ask Codex:
Start the GlobalGPT CLI login process.The CLI opens an authorization page in your browser. Confirm that you initiated the request on your own device, then select Authorize. Do not send your password, verification code, or authorization URL to an AI assistant.
Check the active account privately with:
glbgpt whoamiPrivacy note: This command can display your email address and credit balance, so avoid including its raw output in public screenshots.
Install the GlobalGPT Skills in Codex
The official CLI bundles four Skills for agent applications:
globalgptfor account access and general GlobalGPT tasks.globalgpt-codingfor explicitly delegated coding work.globalgpt-imagefor image generation and editing.globalgpt-videofor video and image-to-video generation.
Install all four with:
glbgpt skill installExpected result: The tested installer reported 4 skills installed and added the bundle to the supported agent Skill directories. Restart Codex or open a new task after installation so the application can load them.
Once loaded, you can make a natural-language request such as:
Use GlobalGPT to research three recent productivity app launches
from official company blogs. Include the title, date, URL, and one
launch-message pattern from each source.Connect GlobalGPT MCP to Codex
The MCP connection exposes GlobalGPT chat, model discovery, image generation, video generation, and task-status functions directly to Codex.
Si glbgpt is available in your normal command path, register the stdio server with:
codex mcp add globalgpt -- glbgpt mcp --max-credits 4000En --max-credits value is a session budget for media generation. Registering the MCP server does not itself generate media or spend credits.
You can also ask Codex to configure it:
Register GlobalGPT as a Codex MCP server using:
glbgpt mcp --max-credits 4000
Then verify that the server is enabled. Do not generate any media yet.Verify the saved configuration:
codex mcp get globalgptcodex mcp listMCP connected: Open a new Codex task after registration. In the tested setup, Codex loaded five GlobalGPT MCP tools.
- Chat with a GlobalGPT model.
- List chat, image, and video models.
- Generate or edit an image.
- Generate a video from text or reference frames.
- Check an image or video generation task.
Build a Complete AI Workflow in Codex
Installation only proves that the commands exist. The more useful question is what the integration adds to real work. To test that, we used GlobalGPT inside Codex to prepare a launch package for a fictional productivity app called FlowNote.
The workflow connected four different capabilities:
- Use a web-enabled LLM to collect current official examples.
- Turn the research into a launch brief.
- Generate a landing-page hero image.
- Animate the visual into an eight-second promotional video.
Each stage used the first valid output. External facts were checked against official pages, while generated media limitations were retained and disclosed.
Step 1: Research Current Information with a Web-Enabled LLM
Tool-capable GlobalGPT chat models can search the web and fetch pages when a question requires current information. The test prompt asked for three recent productivity-product announcements from official company blogs:
Use web search to find three recent productivity app launches or
major product updates announced on official product blogs.
For each example, provide:
- Product name
- Exact announcement title
- Publication date
- Official source URL
- One landing-page or launch-message pattern worth learning from
Use official product or company sources, not news summaries.
Clearly separate verified facts from your recommendations.The first valid response found Asana, Linear, and Notion announcements. We then checked each URL independently. All three returned HTTP 200, and the page titles and publication dates matched the answer.
| Producto | Official announcement | Fecha | Verificación |
|---|---|---|---|
| Asana | Asana Spring 2026 Release | May 20, 2026 | Title and date matched |
| Linear Agent | Introducing Linear Agent | 24 de marzo de 2026 | Title and date matched |
| Notion 3.0 | Introducing Notion 3.0 | September 18, 2025 | Title and date matched |
View the complete first-valid research result
Asana
Observed launch pattern: Start with the organizational problem, explain why current tools fall short, present a unified response, and then support it with feature-level proof.
Linear Agent
Observed launch pattern: Turn abstract capabilities into concrete use cases by showing the user situation, the exact action, and the immediate output.
Notion 3.0
Observed launch pattern: Put a short TL;DR before the longer narrative, followed by the pain point, product vision, demonstrations, use cases, and CTA.
The source titles, dates, and URLs were treated as facts. The launch patterns were the model’s analysis and were not presented as statements made by the companies.
Step 2: Turn the Research into a Launch Brief
The next GlobalGPT MCP call transformed those verified patterns into a practical FlowNote brief. The model defined the audience, core message, three benefits, landing-page structure, visual direction, video concept, and CTA.
Core message: Turn scattered thoughts into focused action.
CTA: Try FlowNote — Capture what matters. Act on what’s next.
View the complete launch brief
Target audience: Knowledge workers, founders, students, and small teams that capture ideas in multiple places and struggle to turn scattered notes into clear next actions.
- Capture without breaking focus: Record ideas, decisions, and tasks in one consistent flow.
- Move from note to next step: Convert selected text into an action with an owner, date, or priority.
- See what matters now: Bring relevant notes and open actions into a focused daily view.
The proposed page structure was: hero and TL;DR, market tension, pain-point story, unified product vision, situation-to-output demonstrations, use cases, and final CTA.
Because FlowNote is fictional, the brief explicitly prohibited unverified customer counts, testimonials, integrations, prices, security certifications, performance claims, and brand endorsements.
Step 3: Generate a Landing-Page Hero Image
The installed globalgpt-image Skill first estimated the job, then generated one 16:9 image with the account’s default image model. The CLI selected Nano Banana 2 and estimated approximately 400 credits.
Create a clean 16:9 hero image for FlowNote, a fictional productivity
app that turns scattered notes into organized daily plans. Show a
modern desktop workspace with disconnected note cards smoothly
converging into one focused daily plan. Use a refined blue-and-violet
palette, soft depth, calm professional lighting, and generous negative
space. No readable text, logos, brand marks, watermarks, people, or
device mockup frames.
Practical result: The composition and color direction worked, but the model added readable interface text despite the prompt. The first valid image was retained.
The image succeeded at the main concept: scattered notes visibly converge toward an organized planner in a blue-and-violet workspace. It did not follow every detail. The interface contains readable words such as “TODAY” and “Tasks,” despite the instruction to avoid readable text. We kept the first valid result instead of rerolling it.
If you want to refine your own prompt, see the Guía rápida de Nano Banana 2. You can also access Nano Banana 2 in GlobalGPT outside the CLI workflow.
Step 4: Turn the Hero Image into a Promo Video
En globalgpt-video Skill used the hero image as the starting frame. The default video route selected Grok Imagine, estimated approximately 800 credits, and returned one eight-second video.
Animate the FlowNote hero image into an 8-second product-launch visual.
Disconnected paper notes and digital task cards should glide smoothly
from left to right and organize themselves into the focused daily
planner on the monitor. Use calm professional motion, subtle blue-and-
violet light trails, a locked camera, and a polished landing-page style.
Preserve the workspace composition. Do not introduce people, logos,
brand marks, watermarks, new readable text, camera shake, or abrupt
transitions.Practical result: The output was playable and preserved the overall workspace idea, but it changed the starting composition substantially.
The returned file was 1280×720, 8.042 seconds long, and encoded with H.264. A representative frame kept the desk, monitor, and note-card concept, but the composition changed substantially and the monitor interface became nearly blank. This is a useful reminder that image-to-video generation may reinterpret a reference frame rather than preserve it exactly.
You can explore the same model through Grok Imagine in GlobalGPT.
What This Workflow Demonstrates
The value is not any single answer or media file. Codex can coordinate the sequence: current web research becomes a brief, the brief becomes a visual direction, and the visual becomes a video. GlobalGPT supplies additional models and media tools while Codex keeps the project context and organizes the work.
| Workflow stage | GlobalGPT capability | Useful output |
|---|---|---|
| Current research | Web-enabled chat model through MCP | Official sources and reusable launch patterns |
| Planificación | GlobalGPT chat model | Structured launch brief with claim boundaries |
| Visual production | GlobalGPT Image Skill | Landing-page hero image |
| Motion production | GlobalGPT Video Skill | Short promotional video |
Useful GlobalGPT CLI Commands
Use this compact reference when you need to check an account, discover a model, or start a generation task.
Setup and account
glbgpt --versionglbgpt loginglbgpt whoamiglbgpt skill installglbgpt mcpglbgpt task show lastModels and generation
glbgpt model list chatglbgpt model list imageglbgpt model list videoglbgpt exec "..." -m <model>glbgpt image "..." --estimateglbgpt video "..." --estimateSolución de problemas
glbgpt: command not found
Close and reopen your terminal first. If the error remains, check whether npm’s global binary directory is included in your shell PATH. Installing the npm package and making the command discoverable are separate steps. You can also ask Codex to locate the installed package and explain which PATH entry is missing.
Codex does not see the newly installed Skills
Run the Skill installer, then restart Codex or open a new task. Skills are loaded when the agent starts; an already-open task may not refresh its Skill inventory automatically.
glbgpt skill installThe MCP server is enabled but no tools appear
Confirm the saved MCP configuration, then open a new Codex task:
codex mcp get globalgptIf Codex starts outside your terminal environment, locate the full GlobalGPT executable path:
command -v glbgptA model returns no output
Treat authentication, transport, provider capacity, and empty responses as operational errors, not proof that the model is weak. Do not keep retrying media generation blindly because an interrupted server-side task may still consume credits. Check the error and task status first.
Preguntas frecuentes
Are GlobalGPT CLI, Skill, and MCP the same thing?
They belong to the same integration, but they have different roles. The CLI supplies commands, the Skills guide Codex’s behavior, and MCP exposes functions as tools.
Can Codex install GlobalGPT CLI for me?
Yes. Give Codex the official command below and ask it to verify the installed version and command entries.
npm i -g @glbgpt/cliDo I need to keep Terminal open?
No. After installation and configuration, Codex can launch the CLI or MCP server when needed. Terminal is useful for setup, verification, and troubleshooting.
Can GlobalGPT models search the web from Codex?
Tool-capable chat models can search the web and fetch pages. Web search may consume additional credits. Always verify important URLs, dates, prices, and product claims against the cited source.
Can I generate images and videos inside Codex?
Yes. The bundled globalgpt-image y globalgpt-video Skills use your GlobalGPT account, and the MCP server also exposes image and video tools.
Does MCP replace the CLI?
No. The MCP server is launched by the CLI. MCP makes the capabilities easier for Codex to call as tools, while the CLI remains the underlying local interface.
How do I switch GlobalGPT accounts?
-
1
Sign out of the current account
glbgpt logout -
2
Start browser authorization
glbgpt login -
3
Verify the active account privately
glbgpt whoami
How do I update GlobalGPT CLI?
Install the current package again:
npm i -g @glbgpt/cliRefresh the bundled Skills, then restart Codex:
glbgpt skill installConclusión final
GlobalGPT CLI turns Codex into a broader multi-model workspace. The CLI handles the local connection, Skills make natural-language delegation predictable, and MCP lets Codex call chat and media tools directly. Once all three are connected, a task can move from current research to structured planning, image generation, and video generation without breaking the workflow into unrelated apps.
If you want to use the same multi-model account outside the command line, you can also open GlobalGPT in your browser.
