Integrations

Connect an AI assistant with the MCP server

Connect an external AI assistant — Claude, or ChatGPT when your account is included in the read-only pilot — to your SceneItAll project so it can read your scenes, breakdown, schedule, and reports. This article covers how to connect, what each assistant can do, and what MCP actually is.

You choose whether the assistant can only read your project, ask before every action, or make changes without asking each time. New connections start with Ask before each operation. See Choose what the assistant can do.

ChatGPT pilot: The ChatGPT connection is read-only. Set the connector access level to Read-only and use the separate ChatGPT URL shown in SceneItAll.

Characters created through an assistant receive the next available production number, just as they do in the app. When the assistant fills gaps in availability, it leaves existing entries unchanged.

MCP is the bridge between your AI assistant and SceneItAll

The Model Context Protocol (MCP) is a standard that lets an AI assistant work with another service. In SceneItAll, it allows a connected assistant to read production information and, when permitted, make changes for you.

The connection belongs to you. The assistant sees only the projects you can access and can do only what your SceneItAll role allows.

Before you start

The assistant connects to the projects you can access, at your role. It can do only what your role allows in the app.
You sign in with your SceneItAll account during setup. You never paste a password into the assistant — you authenticate through the normal SceneItAll sign-in.
AI Connector must be available in your version of SceneItAll. If it is unavailable, the settings panel shows a notice instead of a connection URL.
The ChatGPT browser connection is an invite-only pilot. It also requires an eligible ChatGPT account or workspace where Developer mode and custom apps are available.

ChatGPT plan eligibility and administrator controls can change during the beta. Check OpenAI’s current Developer mode and MCP apps guidance if the menus below are unavailable.

Get your server URL from AI Connector settings

To find your server URL, open the AI Connector settings in the SceneItAll app:

In the top bar, select your avatar.
Choose MCP Connection from the menu. This opens Settings → Account → AI Connector — the single home for the connector (you can also reach it from Profile Settings, then Account → AI Connector).
Choose the connector access level and screenplay-content privacy setting first, then save if you changed either control.
Under Connect an AI assistant, copy the relevant URL. Claude MCP Server URL is the standard full connector. ChatGPT pilot MCP Server URL appears separately only in builds enrolled in the read-only pilot.
Follow the short numbered steps for that assistant, or select Open full setup guide for this article.

Tip: each Copy button copies the URL for that specific connection.

If the panel says that MCP is not configured, the connector is not available in that version of SceneItAll.

Add SceneItAll to Claude as a custom connector

To connect Claude on the web, add SceneItAll as a custom connector:

In Claude, go to Settings, then Connectors, then Add.
For the name, enter SceneItAll.
For the remote MCP server URL, paste the MCP Server URL you copied.
Select Add.

When you connect, you are prompted to sign in with your SceneItAll account, as the panel notes: “You’ll sign in with your SceneItAll account when connecting.” After you sign in, the assistant can act on the projects you can access.

Add SceneItAll to ChatGPT on the web — read-only pilot

If SceneItAll has invited you to the pilot and the AI Connector panel displays a ChatGPT pilot MCP Server URL:

In SceneItAll, set Connector access level to Read-only and save.
Copy the ChatGPT pilot MCP Server URL. Do not use the Claude URL and do not append /sse or /mcp.
Confirm Developer mode is enabled for your ChatGPT account. Depending on your plan and role, an administrator may first need to allow it in Workspace settings → Permissions & roles → Connected data; eligible users enable it under Settings → Apps → Advanced settings or while creating the app.
Open Settings → Apps → Create (or Workspace settings → Apps → Create for an administrator), name the custom app SceneItAll (pilot), and enter the copied URL as its MCP endpoint.
Choose OAuth authentication, select Scan tools, complete the SceneItAll sign-in, review the discovered tools, and create the app.
Start a new chat, enable SceneItAll, and ask ChatGPT to list your projects.

The pilot can select and read project, episode, script, scene, breakdown, element, scenario, and schedule information. It cannot create, change, delete, or approve anything. If the ChatGPT URL is not shown, the pilot is not available for your account or version of SceneItAll.

Set your context, then ask for what you need

Once connected, the assistant sets your working context before it does anything else, then helps you from there:

It lists your projects. One project is selected automatically; with several, it asks you to choose.
It does the same for the episode.
It selects a script revision. The assistant needs a project, episode, and revision before it can continue.
Ask for production work such as scene breakdowns, cast and crew availability, schedule details, call sheets, and reports. Production work uses the latest revision accepted for production. Script comparison, translation, and continuity use the revision you selected.
Optionally, apply a persona (see below) to focus the assistant on one production role.
On the full Claude-compatible connector, what the assistant may do depends on your connector’s permission mode. By default (Ask before each operation), it proposes each step and waits for your “yes” before running it; in Full access it acts without asking; in Read-only every change is blocked; in Blocked it can’t do anything. The ChatGPT pilot must use Read-only and remains read-only even if a broader mode is later selected (see permission modes).
If you do not want the assistant to receive screenplay dialogue or action, enable Script content blocked in the same AI Connector panel. Production metadata remains available.

Talk about days and scenes the way you normally would. Say “Day 3” or “scene 24A.” If a number could refer to more than one item, the assistant asks you to clarify. For example, Main Unit and 2nd Unit can each have a Day 3.

What the assistant can do

The full Claude connection can read project information and make changes when your chosen access level allows it. It covers these areas:

Area	What the assistant can do
Project context	List your projects, set the active project, episode, and required script context, and read a project overview or health dashboard.
Scripts and scenes	List episodes and scripts; list the active episode’s latest production-ready ordinary scenes, copies, and split parts; read scene detail and comments; add notes to the scene Notetaker; group scenes by set or location; update scene fields; and create a light or full independent production-scene copy with an optional reason.
Elements and breakdown	List and inspect elements, read a scene’s breakdown and the cast list, create and recategorize elements (including project-specific custom categories), tag or untag elements on scenes, and permanently delete duplicate or obsolete elements.
Crew, cast, and availability	List crew and cast, search people by name, read the monthly availability grid, and set availability for a person, a date range, or several people at once.
Locations	List filming locations, read location detail, find the scenes at a location, and create or edit a location.
Conflicts	List scheduling conflicts and check what conflicts a proposed schedule change would cause.
Schedule	Read the schedule, one-liner, strips, scenarios, and schedule settings; compare two scenarios; and create or edit scenarios, shoot days, strips, banners, and schedule settings.
Call sheets	Read a day’s call sheet, set its weather note, refresh its production information, and export it to PDF.
Reports	Read the Day Out of Days, the full-fat schedule, a single element’s Day Out of Days, and continuity warnings.
Data completeness	Scan the whole project for fields you haven’t filled in yet — like character prep times that would otherwise fall back to call-sheet defaults — grouped by area, so you can fill the ones that matter.
Search	Run a full-text search across the active project and read that project’s recent notifications plus platform-wide messages.

Check what you haven’t filled in

The assistant can audit your whole project for blank fields that are worth filling — so nothing important is missing from your reports. A common example is character prep times: if you never set a character’s wardrobe or makeup prep minutes, the call sheet quietly falls back to default times, and you might not notice.

Ask the assistant something like “What haven’t I filled in?” and it scans every part of the project — cast, crew, elements, scenes, locations, schedule, and reports — then lists the empty fields, grouped by area, with a note on why each one matters. You can ask it to fill specific values (for example, “set Jane’s makeup prep to 75 minutes”); if your permission mode allows, it makes the change and reminds you to refresh any affected call sheet so the new value shows up.

The audit only ever reports which fields are empty — it never shows the personal or financial data that MCP always keeps private (see What it never returns).

What it never returns

Some data is never exposed to the assistant, regardless of your role:

Personal contact details, addresses, and agency information.
Cast measurements and financial data.

You can also enable Script content blocked. The assistant can still see scene numbers, sluglines, synopses, breakdown elements, page counts, schedules, and reports, but it cannot receive screenplay dialogue, action, or translations.

You decide what the assistant is allowed to do

Set the mode in Settings → Account → AI Connector. SceneItAll applies the setting to every project, and you do not need to reconnect after changing it.

The ChatGPT pilot stays read-only even if you choose a broader access level. Keep the connector set to Read-only while using it. Choose Blocked to turn it off.

Mode	What the assistant can do
Full access	Read project information and make changes without asking before each step.
Ask before each operation (default)	The assistant can act, but checks with you before every operation — it proposes exactly what it’s about to do and waits for your “yes” before running it (see below).
Read-only	Browse, search, and read freely. Every change is blocked — safe exploration.
Blocked	The connector is off: the assistant can’t read or change anything.

If the assistant tries something the current mode doesn’t allow, it gets a clear message and will tell you to change the mode in Settings. A brand-new connector starts in Ask before each operation, so the assistant always checks with you until you give it more (Full access) or less (Read-only / Blocked).

Keep screenplay text out of MCP

Enable Script content blocked below the access-level dropdown to keep screenplay dialogue, action, and translations away from the assistant. This setting is separate from the access level, so an assistant with Full access can still update production information without seeing the screenplay text. It applies to every project and does not require reconnecting.

The setting is off by default. When it is on, the assistant tells you that screenplay content is blocked while still showing the allowed production details.

How “Ask” works. SceneItAll can’t pop up a window inside your AI app, so the approval happens in your chat: when the assistant wants to do something, it shows you exactly what (e.g. “set scene 5 to NIGHT?”) and waits. Only after you say yes does it actually run that step. Nothing happens until you approve — and because it covers every operation, expect to approve routine lookups too, not just changes.

Tip: to stop an assistant mid-task, switch the connector to Read-only or Blocked — it takes effect within ~15 seconds.

It only ever sees what you can see

Your permissions apply. The assistant can access only the projects and actions available to your SceneItAll role.
You choose what it can do. Ask before each operation makes the assistant check with you every time. Read-only blocks changes, and Blocked turns the connector off. Script content blocked controls screenplay access separately. Change these settings in Settings → Account → AI Connector.
No personal data exposed. Contact details, addresses, agency info, measurements, and financial data are never returned by MCP tools.
Your connection is protected. SceneItAll does not store or log the reusable secret in readable form.
Usage limits apply. The connector follows the same usage limits as the app.

Changes stay connected

The assistant follows the same rules as the app. Production work uses the latest revision accepted for production, while script comparison, translation, and continuity use the selected revision.

Editing or refreshing a report does not change the script, breakdown, crew, or schedule. Whether the assistant can make a particular change depends on your connector access level.

Apply a persona to focus on one production role

A persona is a starting-point prompt — not a SceneItAll role, and it doesn’t change your permissions. It shapes how the assistant prioritizes work and what it flags. The server offers five:

Persona	Focuses the assistant on
`first_ad`	Schedule integrity, conflicts, turnaround, crew logistics, and shoot-day planning.
`script_supervisor`	Continuity, scene ordering, script-day logic, and time-of-day analysis.
`line_producer`	Cost-aware scheduling, hold-day analysis, overtime prevention, and crew logistics.
`location_manager`	Permits, location grouping, company moves, travel logistics, and weather contingency.
`casting_director`	Cast availability windows, hold days, actor scheduling conflicts, and deal-aware scheduling.

Apply a persona in your assistant the way it offers prompts, then ask your question as usual.