How do I create a new course storyboard?
Ask: "Create a Content Studio project called Workplace Safety, then add eight slides from this outline." To create projects, your connection needs all-projects coverage and write permission.
Model Context Protocol
Ask your AI assistant to work on Content Studio storyboards and media or configure AI Interactions for Storyline and HTML. Choose a product, then follow its connection guide.
Connect your AI assistantMCP connects your AI assistant to Cluelabs. You choose which resources it can access and whether it can make changes.
Navigation
Choose your app, then follow its sign-in or API token instructions. Menu names may vary with your app version and your organization's settings.
Connection options
Content Studio supports both methods. Choose the one offered by your app.
| Your app | Connection options |
|---|---|
| ChatGPT on the web | OAuth sign-in |
| ChatGPT desktop | API token through a direct MCP connection |
| Claude Desktop or Claude on the web | OAuth sign-in or API token |
| Gemini CLI | OAuth sign-in or API token |
| Gemini Enterprise | OAuth through an administrator; requires a compatible client setup |
| Google Antigravity | OAuth sign-in or API token |
| Visual Studio Code | OAuth sign-in or API token |
| Kiro | OAuth sign-in or API token |
Use this server address for either method: https://cluelabs.com/api/cluelabs/content/mcp.
Some apps need an approved OAuth client ID or connection settings before sign-in. These identify the app and are different from an API token; contact Cluelabs for the settings for your app.
The OAuth file examples request read and write access. For whole-project deletion, ask Cluelabs for settings that also request management permission. These guides connect to Content Studio; other Cluelabs tools may use different settings.
AI Interaction
Use an account API token to inspect or edit Storyline and HTML interactions, including their instructions, knowledge base, variables, and optional web files. Choose the interactions and permission level your assistant needs.
Server address:
https://cluelabs.com/api/cluelabs/interaction/mcp This connection uses Streamable HTTP with Authorization: Bearer YOUR_API_TOKEN. Create the token in Account Security; the editor displays your interaction ID without exposing a reusable editing credential.
After connecting, ask the assistant to call list_interactions. A successful list, even an empty one, confirms access. Seeing the catalogue alone does not.
Your permissions
Your AI app sends you to Cluelabs to sign in and choose what it can do.
The choices shown depend on the access the app requests and your current project permissions. Generating narration, graphics, sound effects, or music can spend your Cluelabs credits.
Start a new conversation and ask: "Use Content Studio to list my projects." Allow the request if prompted. A project list, or a successful empty list, confirms access; seeing tool names alone does not.
Open Account Security, find Connected apps, and select Disconnect for the approval you want to end. This stops new requests; work already accepted may still finish.
Removing an app from your AI assistant does not disconnect it in Cluelabs. Reconnecting creates a separate approval, so disconnect old entries you no longer use.
For more permissions, start a new sign-in and choose project coverage again. If the permission you need is missing, the app must request it before you approve.
If your app asks you to sign in again, repeat the approval steps. Your app normally renews the connection while it is in use.
Authentication
An API token is a private access key you create in Cluelabs and paste into your AI app. Use this option when you prefer a token or your app does not support Cluelabs sign-in.
https://cluelabs.com/api/cluelabs/content/mcpAuthorization: Bearer YOUR_API_TOKENIn the examples below, replace YOUR_API_TOKEN with your token. Keep Bearer and the space before it; keep the token private and out of shared files.
After connecting, ask: "Use Content Studio to list my projects." To stop token access later, return to Account Security and revoke the token.
AI Interaction
10), write access (20), or all permissions (250). A single-resource grant cannot exceed your current access. An all-resource grant is a ceiling; current ownership and sharing still limit every operation.Creating interactions requires all-resource write or all-permissions scope. A single-interaction token cannot create another interaction. Whole-interaction deletion also requires current ownership; a collaborator with level 250 cannot delete the interaction.
Editors can disable logging or create a new table owned by the interaction owner. Below effective level 250, a changed positive table selection retains the existing binding while the rest of the save succeeds. At level 250 a replacement table must belong to the interaction owner.
Existing connections must be reconfigured manually with an account token and explicit interaction IDs.
Client Integration
Connect with an API token in ChatGPT desktop, or sign in to Cluelabs through a ChatGPT web plugin.
cluelabs-content-studio, choose Streamable HTTP, and enter https://cluelabs.com/api/cluelabs/content/mcp.~/.codex/config.toml (%USERPROFILE%\.codex\config.toml on Windows). Update this server's existing entry to match the example below; replace YOUR_API_TOKEN. Keep other entries.[mcp_servers.cluelabs-content-studio]
url = "https://cluelabs.com/api/cluelabs/content/mcp"
http_headers = { Authorization = "Bearer YOUR_API_TOKEN" }
Keep this file private: it contains your token. Select Restart in the MCP settings. In a local desktop chat, use /mcp to check the connection, then ask it to list your Content Studio projects. A successful result confirms token access.
This direct desktop connection uses the configuration shared with Codex. ChatGPT web plugins have separate authentication settings. See OpenAI's desktop MCP setup and header configuration.
Use ChatGPT on the web. Your account or workspace must allow custom MCP plugins; this setup uses Cluelabs sign-in rather than an API token.
https://cluelabs.com/api/cluelabs/content/mcp as the Server URL.Start a new conversation and ask: "Use Content Studio to list my projects." Allow the request if prompted. A project list, or a successful empty list, confirms access; seeing tool names alone does not.
See OpenAI's custom MCP setup guide for current screens and settings.
Ask: "Create a Content Studio project called Workplace Safety, then add eight slides from this outline." To create projects, your connection needs all-projects coverage and write permission.
Yes. Ask it to find the project by name, review the slides, and suggest changes. When you are ready, ask it to save the revised slide text or notes.
Ask: "Check the voice settings for my Workplace Safety project and generate narration for the approved slides." Audio generation uses credits and may take time to finish.
Ask it to show the available style presets, then apply the one you choose. You can also ask it to update the project's colors, fonts, and visual guidelines.
Yes. Ask it to shorten the on-screen text while keeping the detailed explanation in the narration script. Review the wording before asking it to save.
Ask it to review the lesson and add a multiple-choice question with answer feedback and notes for the course builder. You can edit the result in Content Studio.
Yes. Ask it to save a standalone narration script for a course introduction, disclaimer, or closing message. You can then ask it to generate the audio.
Save the revised script and generate new narration first. Once the audio is ready, ask for captions for that audio file in the language you need.
AI Interaction
cluelabs-interaction, choose Streamable HTTP, and enter https://cluelabs.com/api/cluelabs/interaction/mcp.~/.codex/config.toml (%USERPROFILE%\.codex\config.toml on Windows). Update this server's existing entry to match the example below; replace YOUR_API_TOKEN. Keep other entries.[mcp_servers.cluelabs-interaction]
url = "https://cluelabs.com/api/cluelabs/interaction/mcp"
http_headers = { Authorization = "Bearer YOUR_API_TOKEN" }
Keep this file private: it contains your token. Select Restart in the MCP settings. In a local desktop chat, use /mcp to check the connection, then ask it to list your AI Interactions. A successful result confirms token access.
This direct desktop connection uses the configuration shared with Codex. ChatGPT web plugins have separate authentication settings. See OpenAI's desktop MCP setup and header configuration.
Ask ChatGPT to call list_interactions. AI Interaction uses API tokens; the OAuth setup for authenticated ChatGPT web plugins does not configure this token connection.
Client Integration
Connect through Claude's connector settings with OAuth sign-in or an API token.
In Claude Desktop or Claude on the web, open Customize > Connectors, select + Add, then Add custom connector. Enter Cluelabs Content Studio and the server address https://cluelabs.com/api/cluelabs/content/mcp, then select Continue.
For a team account, an owner may need to add it first in Organization settings > Connectors.
authorization, enter Bearer YOUR_API_TOKEN with your token, and mark it Required. Include the space after Bearer; Claude sends the value exactly as entered.Request headers are currently available only to some Claude organizations. If that setting is missing, use OAuth or the Claude Desktop option below.
This option uses a helper called mcp-remote and requires Node.js on your computer.
claude_desktop_config.json.{
"mcpServers": {
"cluelabs-content-studio": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://cluelabs.com/api/cluelabs/content/mcp",
"--header",
"Authorization:${AUTHORIZATION}"
],
"env": {
"AUTHORIZATION": "Bearer YOUR_API_TOKEN"
}
}
}
}YOUR_API_TOKEN with your token. Leave Authorization:${AUTHORIZATION} as shown.See the mcp-remote setup guide for helper settings.
On a team account, a fixed token may be used by everyone with access to that connector. Choose a token limited to the projects and permissions the team needs.
Start a new conversation and ask: "Use Content Studio to list my projects." Allow the request if prompted. A project list, or a successful empty list, confirms access; seeing tool names alone does not.
See Claude's custom connector guide and request header instructions for current screens and availability.
Give Claude your outline and ask it to create a Content Studio project with slide titles, narration, on-screen text, and notes for the course builder. Creating a project requires all-projects coverage and write permission.
Ask: "Review the narration in my Customer Service project, make it more conversational, and save the revised scripts." Claude can update several slides in one request.
Yes. Ask it to review the project's style and graphics settings, then draft image prompts that follow those guidelines.
Attach the manual and ask Claude to break it into lessons and slides. Review the proposed structure, then ask it to save the slides in Content Studio.
Ask it to review the scripts for jargon and long sentences, suggest plain-language replacements, and save the changes you approve.
Ask Claude to check the project's reference images and visual guidelines before writing image prompts. Use the same character and style details across the slides.
Ask it to show voices for your course language, then save the voice you choose. You can also ask it to adjust the speaking speed.
Yes. Describe the order you want, such as moving the practice activity before the summary. Ask Claude to show the revised order before saving it.
AI Interaction
https://cluelabs.com/api/cluelabs/interaction/mcp. Select Continue and review the detected settings.authorization, enter Bearer YOUR_API_TOKEN with your token, and mark it Required. Include the space after Bearer; Claude sends the value exactly as entered.On a team account, an owner adds the connector in Organization settings > Connectors > Add > Custom; choose Web if asked. Dialog layouts vary by organization.
Header authentication is available to a limited set of organizations. See Claude's current header instructions.
With Node.js installed, open Settings > Developer > Edit Config and merge this entry into claude_desktop_config.json. Replace the token placeholder, save, completely quit and reopen Claude Desktop.
{
"mcpServers": {
"cluelabs-interaction": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://cluelabs.com/api/cluelabs/interaction/mcp",
"--header",
"Authorization:${AUTHORIZATION}"
],
"env": {
"AUTHORIZATION": "Bearer YOUR_API_TOKEN"
}
}
}
} The helper's own documentation explains header forwarding and the space-free argument used on Windows.
The local Desktop helper is unavailable on the web. If your web connector has no Request headers setting, this Interaction connection cannot authenticate there; use a supported token-capable client. On shared connectors, the token's scope applies to everyone using that credential.
Ask Claude to call list_interactions and return the IDs and modes.
Client Integration
Use OAuth sign-in or an API token with Gemini CLI. See the separate administrator instructions for Gemini Enterprise below.
Gemini CLI runs in your computer's terminal. Open your user settings file, ~/.gemini/settings.json, and add one of the examples below; keep any settings already there.
YOUR_APPROVED_CLIENT_ID with that ID.{
"mcpServers": {
"cluelabs-content-studio": {
"httpUrl": "https://cluelabs.com/api/cluelabs/content/mcp",
"oauth": {
"enabled": true,
"clientId": "YOUR_APPROVED_CLIENT_ID",
"scopes": [
"content:read",
"content:write"
]
}
}
}
}gemini in your terminal./mcp auth cluelabs-content-studio. On the Cluelabs page, sign in and choose the projects and permissions, then select Approve connection.{
"mcpServers": {
"cluelabs-content-studio": {
"httpUrl": "https://cluelabs.com/api/cluelabs/content/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
}YOUR_API_TOKEN with your token, save the file, and start a new Gemini CLI session.Enter /mcp to check the connection.
Start a new conversation and ask: "Use Content Studio to list my projects." Allow the request if prompted. A project list, or a successful empty list, confirms access; seeing tool names alone does not.
See Gemini CLI's MCP guide for current screens and settings.
The Gemini app, Gemini CLI, and Gemini Enterprise have different connection settings. Enterprise uses a Google Cloud data store and requires an administrator.
Google's Enterprise form requires an OAuth client ID and client secret. Cluelabs's current OAuth setup uses clients without a secret, so an administrator must arrange a compatible setup with Cluelabs first; an API token cannot replace the client secret.
See Google's Enterprise setup guide for current screens and settings.
Yes. Ask it to read your local notes and create a Content Studio project with the lesson structure you describe. Creating projects requires all-projects coverage and write permission.
Ask it to find your project, add a knowledge check after the lesson, and move the summary to the end. Review the new content and order.
Ask Gemini to show voices for your course language and save your choice. You can also ask it to adjust the speaking speed.
Yes. Identify the project and image, then describe the change, such as changing a character's pose. Image generation and editing use your Cluelabs credits.
Ask it to list the storage zones available to your account. Choose a zone before asking it to create the project.
Ask it to draft sound effect prompts for correct answers, hints, or button clicks. Review those prompts before asking it to generate audio.
Ask it to find the image in your project and upscale it. This starts a generation task that uses credits; check the finished image in Content Studio.
Yes. Give it a naming pattern and ask it to rename the narration or image files in a specific project.
AI Interaction
Merge this entry into the mcpServers map in your Gemini CLI ~/.gemini/settings.json. Replace the token placeholder, save, and start a new CLI session. Use /mcp to check connection status, then ask it to call list_interactions.
{
"mcpServers": {
"cluelabs-interaction": {
"httpUrl": "https://cluelabs.com/api/cluelabs/interaction/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
} See Gemini CLI's HTTP and custom-header configuration.
This Interaction release adds no Gemini Enterprise OAuth setup. Use the Gemini CLI token configuration above where available. Content Studio's administrator OAuth instructions do not configure AI Interaction.
Client Integration
Connect Antigravity to Content Studio with OAuth sign-in or an API token.
In Antigravity IDE, open the agent panel's ... menu, select MCP Servers > Manage MCP Servers > View raw config. Add one example below, keeping existing entries.
{
"mcpServers": {
"cluelabs-content-studio": {
"serverUrl": "https://cluelabs.com/api/cluelabs/content/mcp",
"oauth": {
"clientId": "YOUR_APPROVED_CLIENT_ID"
}
}
}
}{
"mcpServers": {
"cluelabs-content-studio": {
"serverUrl": "https://cluelabs.com/api/cluelabs/content/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
}YOUR_API_TOKEN with your token, save, and refresh the server list.Start a new conversation and ask: "Use Content Studio to list my projects." Allow the request if prompted. A project list, or a successful empty list, confirms access; seeing tool names alone does not.
See Antigravity's MCP guide for current screens and settings.
Ask it to read your course outline or source notes and save a storyboard in Content Studio. Specify the project name and the slide content you want.
Yes. Ask it to draft prompts that match the lesson or activity, then generate the clips you approve. Generation uses your Cluelabs credits.
Ask: "Use Content Studio to list my projects." A successful list confirms access. Then ask it to show the slides for one project.
Ask it to check the scripts and media prompts before generating narration, graphics, sound effects, or music. Each request starts a task; it does not mean the files are already finished.
Give it the updated product notes and ask it to compare them with the storyboard. Ask it to suggest and save changes to the affected slides.
Ask it to list the files it proposes removing and explain why. Review the list before approving deletion.
Ask it to read your brand document and update the project's colors, fonts, and visual guidelines to match.
Ask it to estimate the spoken time for each slide and flag scripts that may be too long. Review its suggestions before changing the narration.
AI Interaction
In Antigravity IDE, open the MCP servers panel and its raw configuration. Merge this remote server into mcp_config.json, replace the token placeholder, save, and refresh the server connection. Ask it to call list_interactions.
{
"mcpServers": {
"cluelabs-interaction": {
"serverUrl": "https://cluelabs.com/api/cluelabs/interaction/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
} The Antigravity documentation specifies Streamable HTTP and custom headers for remote servers.
Client Integration
Connect Visual Studio Code to Cluelabs Content Studio using GitHub Copilot Chat and VS Code's built-in MCP support.
Sign in to GitHub Copilot in VS Code. Press Ctrl+Shift+P on Windows/Linux or Cmd+Shift+P on macOS, then run MCP: Open User Configuration.
Add one example below to your mcp.json file, keeping any existing entries. These examples use VS Code's user-profile format.
YOUR_APPROVED_CLIENT_ID with the approved VS Code client ID from Cluelabs.{
"servers": {
"cluelabs-content-studio": {
"type": "http",
"url": "https://cluelabs.com/api/cluelabs/content/mcp",
"oauth": {
"clientId": "YOUR_APPROVED_CLIENT_ID"
}
}
}
}{
"servers": {
"cluelabs-content-studio": {
"type": "http",
"url": "https://cluelabs.com/api/cluelabs/content/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
}YOUR_API_TOKEN with your token, save, and start Content Studio through MCP: List Servers.Open Copilot Chat, select an agent that can use tools, and enable Content Studio in the tool picker.
Start a new conversation and ask: "Use Content Studio to list my projects." Allow the request if prompted. A project list, or a successful empty list, confirms access; seeing tool names alone does not.
If it fails, use MCP: List Servers > cluelabs-content-studio > Show Output to see the connection error.
See VS Code's MCP configuration guide for current screens and settings.
Yes. Ask it to open your Content Studio project and improve the text on a particular slide. You can ask for a draft first, then ask it to save.
Ask it to save the revised scripts and generate new narration. Once the audio is ready, ask it to create captions in the course language.
Ask it to read the storyboard first and identify the slide by its title and number. Confirm the target before asking it to save changes.
Ask it to compare the lesson with your activity instructions and update the slide's developer notes. Those notes help the course builder assemble the activity in the authoring tool.
Yes. Open the outline and ask Copilot Chat to create the project and slides in Content Studio. Creating projects requires all-projects coverage and write permission.
Ask it to review the lessons and suggest music for introductions, exercises, or summaries. You can save the prompts before deciding whether to generate the clips.
Give it a naming pattern and ask it to rename the audio files in the project. Ask it to show the proposed names first if you want to review them.
Yes. Ask it to list the prompts it proposes deleting, then approve the cleanup after reviewing that list.
AI Interaction
Open your VS Code .vscode/mcp.json or user MCP configuration and merge the server below. Replace the token placeholder in your private configuration, save, start the server, enable its tools in the chat, and ask it to call list_interactions.
{
"servers": {
"cluelabs-interaction": {
"type": "http",
"url": "https://cluelabs.com/api/cluelabs/interaction/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
} Keep populated credentials out of source control. This is the VS Code configuration format; other harnesses may use different configuration and credential handling. See the VS Code MCP reference.
Client Integration
Connect Kiro to Content Studio with OAuth sign-in or an API token.
In Kiro, press Ctrl+Shift+P on Windows/Linux or Cmd+Shift+P on macOS. Select Kiro: Open user MCP config (JSON) to open ~/.kiro/settings/mcp.json.
Add one example below, keeping existing entries. Make sure MCP support is enabled in Kiro's settings.
{
"mcpServers": {
"cluelabs-content-studio": {
"url": "https://cluelabs.com/api/cluelabs/content/mcp",
"oauth": {
"clientId": "YOUR_APPROVED_CLIENT_ID",
"redirectUri": "YOUR_APPROVED_REDIRECT_URL",
"oauthScopes": [
"content:read",
"content:write"
]
}
}
}
}{
"mcpServers": {
"cluelabs-content-studio": {
"url": "https://cluelabs.com/api/cluelabs/content/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
}YOUR_API_TOKEN with your token and save. Kiro reloads the connection.Start a new conversation and ask: "Use Content Studio to list my projects." Allow the request if prompted. A project list, or a successful empty list, confirms access; seeing tool names alone does not.
See Kiro's MCP configuration guide for current screens and settings.
Give it a plan with learning objectives and lesson content, then ask it to create the project and slides in Content Studio. Creating projects requires all-projects coverage and write permission.
Ask it to read the slide notes and draft prompts for sound effects or music. Review the prompts before asking it to generate the audio.
Ask it to read the source storyboard, create a new project, and copy the slides in order. Specify whether you also want the project settings copied; generated media needs separate copying or regeneration.
Give it the revised plan and ask it to compare that plan with the existing slides. Ask it to update only the affected content.
Ask it to find missing scripts or incomplete slide notes. Review the omissions before starting narration generation.
Yes. Ask it to upload your reference images to the project and use them in the project's graphics settings.
Ask it to save your approved disclaimer as a standalone narration script in the projects you name. Your connection must allow access to each project.
Ask it to list the projects it proposes deleting and confirm the list before proceeding. Whole-project deletion requires management permission and current ownership.
AI Interaction
In Kiro IDE, use the command palette to open the user MCP configuration at ~/.kiro/settings/mcp.json. Merge this server, replace the token placeholder, and save to reconnect. Ask Kiro to call list_interactions.
{
"mcpServers": {
"cluelabs-interaction": {
"url": "https://cluelabs.com/api/cluelabs/interaction/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
} See Kiro's remote-header configuration. Workspace configuration can override user entries.
Product Capabilities
Ask your assistant to review a storyboard, edit slides, choose styles and voices, or start and track media generation. Use the 65 tool names below as a reference.
list_projects: Lists the Content Studio projects allowed by your connection, with their names and IDs.create_project: Creates a new storyboard project with initial parameters, returning the newly assigned project ID.rename_project: Renames an existing Content Studio project.delete_project: Permanently removes a storyboard project and its associated metadata.get_storage_zones: Lists storage zones with their IDs, names, account-default status, and availability under your plan.get_task_status checks a generation batch using its chain ID and reports its status and task counts.get_storyboard_settings: Retrieves project-level instructional settings including target duration, audience profile, pacing, and slide density.update_storyboard_settings: Updates instructional parameters and pacing preferences for a project.get_storyboard_file prepares a DOCX, CSV, PDF, or JSON download from a saved storyboard.get_slides: Loads all slides in a project, including slide IDs, titles, narration scripts, on-screen text, visual directions, developer notes, and interaction plans.create_slide: Adds a new slide to an existing project with specified titles and instructional copy.update_slide: Saves selected fields at one slide ID, creating a slide data entry if that ID does not exist. This does not add the ID to the storyboard's slide order.update_slides_bulk: Saves selected fields at multiple slide IDs in one request, creating missing slide data entries without adding them to the slide order.delete_slide: Removes an individual slide from the storyboard.reorder_slides: Updates the sequential slide order of the course.list_style_presets: Lists all ready-to-use design presets for color palettes, typography, and UI component styling.get_style_preset: Retrieves the full configuration of a specific style preset by identifier.get_style_settings: Retrieves the active visual style rules and color tokens configured for a project.save_style_settings: Saves brand colors, typography choices, and visual system guidelines for a project.list_voices: Lists all available text-to-speech voices across supported providers, languages, and regional accents.get_default_voice: Returns the system default narration voice profile.get_voice_settings: Retrieves project-level voice settings, including voice provider, speed, pitch, stability, and delivery tone.save_voice_settings: Configures voice selection and delivery settings to maintain vocal consistency across slides.generate_narrations Queues voiceover for narration.list_narrations: Lists generated voiceover audio files associated with a project.rename_narration: Renames a generated narration audio file.update_narration_metadata: Updates descriptive metadata and tags for an audio track.delete_narrations: Removes generated voiceover files from a project.generate_captions: Queues SRT caption generation for an existing narration MP3, using its filename and language, with an optional transcript to help alignment.get_custom_narration_scripts: Retrieves custom standalone narration scripts not tied to standard slide timelines.save_custom_narration_script: Saves an individual custom narration script with a stable identifier.bulk_save_custom_narration_scripts: Saves multiple custom narration scripts simultaneously.delete_custom_narration_script: Deletes a standalone custom narration script.get_graphics_settings: Retrieves graphics generation settings, active art styles, and reference image anchors.save_graphics_settings: Saves graphic generation guidelines and visual rules for a project.list_graphics_images: Lists generated and uploaded graphic image assets for a project.save_graphics_prompt: Saves an image generation prompt for a specific slide.bulk_save_graphics_prompts: Saves image generation prompts across multiple slides at once.delete_graphics_prompt: Deletes an image prompt from a slide.upload_graphics_image: Uploads reference images or character art to anchor visual consistency across slides.generate_graphics: Queues generation of custom course graphics from slide prompts and project style rules.edit_graphics_image: Submits an image modification instruction to edit an existing graphic asset.upscale_graphics_image: Queues an image upscaling task to increase resolution for high-DPI displays.rename_graphics_image: Renames a graphic image asset.delete_graphics_images: Removes graphic images from a project.list_sfx_prompts: Lists sound effect prompt suggestions derived from slide interaction notes.save_sfx_prompt: Saves a sound effect prompt for a slide event or interaction.bulk_save_sfx_prompts: Saves multiple sound effect prompts at once.delete_sfx_prompt: Deletes a sound effect prompt.bulk_delete_sfx_prompts: Deletes multiple sound effect prompts in a single batch.generate_sfx: Queues custom sound effect generation using AI audio synthesis.list_sfx: Lists generated sound effect audio clips in a project.rename_sfx: Renames a sound effect audio clip.update_sfx_clip: Updates metadata or prompt tags for a sound effect clip.delete_sfx: Deletes sound effect clips from a project.list_music_prompts: Lists music prompt suggestions matching lesson themes and pacing.save_music_prompt: Saves a music generation prompt.bulk_save_music_prompts: Saves multiple music prompts in a single batch.delete_music_prompt: Deletes a music prompt.bulk_delete_music_prompts: Deletes multiple music prompts simultaneously.generate_music: Queues generation of music tracks tailored to course mood and duration.list_music_clips: Lists generated music clips in a project.rename_music_clip: Renames a music audio track.update_music_clip: Updates metadata or prompt notes for a music track.delete_music_clips: Deletes music tracks from a project.AI Interaction capabilities
Choose IDs from list_interactions. Existing-resource calls require a positive interaction_id. Read operations require 10, ordinary writes require 20, and deletion requires 250 plus actual ownership. The storage-zone helper accepts any valid supported account token.
| Tool | Inputs | Results | Access |
|---|---|---|---|
list_interactions | {} | interactions | 10 |
create_interaction | name, folder_id, zone_gcp, settings, content | interaction | 20 |
get_interaction | interaction_id | interaction | 10 |
update_interaction | interaction_id, settings, content | interaction | 20 |
rename_interaction | interaction_id, name | interaction_id, name, saved_at | 20 |
delete_interaction | interaction_id | interaction_id, deleted | 250 |
get_storage_zones | {} | zones | 0 |
list_interaction_files | interaction_id | interaction_id, display_url, mode, web_mode_active, files, images | 10 |
get_interaction_file_contents | interaction_id, file_path | file_path, content, size | 10 |
update_interaction_file | interaction_id, file_path, content | interaction_id, saved, saved_at | 20 |
upload_interaction_image | interaction_id, filename, content_base64 | interaction_id, name, path, mime, width, height, resized | 20 |
delete_interaction_image | interaction_id, image_path | interaction_id, deleted | 20 |
get_interaction_display_url | interaction_id | interaction_id, display_url, mode, web_mode_active | 10 |
get_interaction_context | interaction_id | interaction_id, mode, settings, content, display, editing_surface | 10 |
Creation and configuration saves complete synchronously, including required knowledge-base processing. File writes validate code and provision missing companions without overwriting edits; images retain existing sanitization and size limits. A display URL does not establish successful HTML playback.
Yes. Lifecycle and configuration tools support Storyline and HTML. Workspace edits leave the active mode unchanged.
Single-resource tokens reach that ID within your current access. All-resource tokens cover currently accessible resources, including later creations and shares, capped by the token level.
Reads list only existing files. A Storyline interaction can have no web workspace. Reading a missing file returns file_not_found; deleting a missing image returns image_not_found. Storage outages are reported separately.
Use an account token in the Authorization header and a returned interaction ID in tool arguments. Browser sessions and public runtime URLs do not authenticate MCP editing.
Inspect the identified resource with get_interaction or list_interactions. Do not automatically repeat creation. Deliberately update the known ID, or retry deletion only if the owned interaction remains.
Get Started
Choose your product and app, follow its supported authentication instructions, and ask the assistant to list the resources your connection can access.