---
title: What the Scenario MCP is, and how to connect it
display: 'What the *Scenario* MCP is, and how to connect it'
nav_title: What the Scenario MCP is, and how to connect it
summary:
  - "The Scenario MCP lets your own AI agent run Scenario models, workflows and assets from a plain-language request, billed in the same credits as the web app."
  - "Add https://mcp.scenario.com/mcp to your AI client, sign in once in the browser, and confirm with a free request."
  - "Add Scenario's open-source skills so the agent follows tested procedures, and use the API instead for fixed, unattended code."
description: What the Scenario MCP does and when to use it, the exact setup for Claude, Cursor, VS Code, Codex and other clients, and Scenario's agent skills.
section: mcp
order: 10
type: guide
level: Automate
roles: [all]
time: { read: 12, do: 10 }
needs: ["A Scenario account", "An AI client that supports remote tool servers", "Node.js, to install the skills"]
last_verified: 2026-11-11
models_checked: ["GPT Image 2.5 Sunburst"]
hero: mcp/connect-scenario-mcp/ask-your-agent.webp
related: [first-session-with-scenario-mcp, scenario-agents-overview]
thumb: mcp/what-is-scenario-mcp/thumb.webp
video: tutorials/what-is-scenario-mcp.mp4
video_caption: "The Scenario MCP, Part 1: What it is and how to connect it"
chapters:
  - { at: 0, title: "What the MCP connects", image: "/media/images/mcp/what-is-scenario-mcp/ch-01-what-the-mcp-connects.webp" }
  - { at: 23, title: "Ask your assistant for a picture", image: "/media/images/mcp/what-is-scenario-mcp/ch-02-ask-your-assistant-for-a-picture.webp" }
  - { at: 32.5, title: "What a skill adds", image: "/media/images/mcp/what-is-scenario-mcp/ch-03-what-a-skill-adds.webp" }
  - { at: 44.5, title: "Add the skill in Claude", image: "/media/images/mcp/what-is-scenario-mcp/ch-04-add-the-skill-in-claude.webp" }
  - { at: 60, title: "Let the skill do a whole job", image: "/media/images/mcp/what-is-scenario-mcp/ch-05-let-the-skill-do-a-whole-job.webp" }
  - { at: 87, title: "Add the Scenario MCP as a custom connector", image: "/media/images/mcp/what-is-scenario-mcp/ch-06-add-the-scenario-mcp-as-a-custom-connector.webp" }
  - { at: 104.5, title: "Connect and authorize", image: "/media/images/mcp/what-is-scenario-mcp/ch-07-connect-and-authorize.webp" }
  - { at: 114.5, title: "Find more skills", image: "/media/images/mcp/what-is-scenario-mcp/ch-08-find-more-skills.webp" }
  - { at: 132.5, title: "Check with a free question", image: "/media/images/mcp/what-is-scenario-mcp/ch-09-check-with-a-free-question.webp" }
  - { at: 147, title: "Recap", image: "/media/images/mcp/what-is-scenario-mcp/ch-10-recap.webp" }
steps:
  - title: "Ask your assistant for a picture"
    text: "With Scenario connected, open a new chat and start with \"Using Scenario\" and the project name. The assistant picks a model, runs it and shows the image with asset_display, with a View in Scenario link."
    prompt: |-
      Using Scenario, make a picture of a red fox curled up in the snow, in my project Brand Studio.
  - title: "Understand what a skill adds"
    text: "A skill is a folder with a SKILL.md file: a name, when to use it, then the procedure. The scenario-3d skill makes a concept image first, then runs image-to-3D."
  - title: "Add the skill in Claude"
    text: "In claude.ai, Customize › Skills › Add › Upload skill, choose the .zip or .md file, check the Preview and click Upload."
  - title: "Let the skill do a whole job"
    text: "In a new chat, name the skill in the request. Download the model as a .glb, then in Blender File › Import › glTF 2.0 (.glb)."
    prompt: |-
      Use the Scenario 3D skill: make a fantasy lantern as a 3D model I can use in Blender, in my project Brand Studio.
  - title: "Copy the address from mcp.scenario.com"
    text: "On mcp.scenario.com › Installation, keep OAuth selected, pick your assistant's tab (here Claude.ai) and click Copy next to https://mcp.scenario.com/mcp."
  - title: "Add a custom connector in Claude"
    text: "Customize › Connectors › Add › Add custom connector: name it Scenario, paste the address as the server URL and click Continue. Keep Sign in now and Register automatically as detected, leave Request headers empty, and click Add."
  - title: "Connect and authorize"
    text: "Click Connect, then Authorize on the Scenario page. Under Tool permissions, allow the read-only tools if approvals slow you down."
  - title: "Find more skills"
    text: "Get more skills from github.com/scenario-labs/skills (the skills folder, with dcc for Blender, Maya and ZBrush) or from the Skill button of any Exploration on scenario.com/explorations."
  - title: "Check with a free question"
    text: "Ask something that needs a Scenario tool but generates nothing. A working connection answers from a tool call, such as Listed Scenario teams, with your project and its team."
    prompt: |-
      Can you see my Scenario project Brand Studio?
agent_steps:
  - title: "Add the Scenario MCP to your assistant"
    text: "Add https://mcp.scenario.com/mcp as a custom connector (in Claude, Customize › Connectors › Add › Add custom connector), or with your client's command from the Other assistants table, such as `claude mcp add --transport http --scope user scenario https://mcp.scenario.com/mcp` in Claude Code."
  - title: "Sign in once"
    text: "Click Connect, log in to Scenario and click Authorize. OAuth needs no key; never paste a key or secret into the chat."
  - title: "Check with a free question"
    text: "A working connection answers from a tool call with your team and project. If it answers from memory or asks for a key, see Common problems."
    prompt: |-
      Can you see my Scenario project Brand Studio?
  - title: "Ask for a first picture"
    text: "Say \"Using Scenario\" and name the project. Ask for the quote before any batch or video."
    prompt: |-
      Using Scenario, make a picture of a red fox curled up in the snow, in my project Brand Studio.
  - title: "Add a skill and let it do a whole job"
    text: "Upload a skill in Customize › Skills, or in a code tool run `npx skills add scenario-labs/skills --skill scenario` and restart the agent. Then name the skill in the request; the 3D skill makes a concept first, then the 3D model."
    prompt: |-
      Use the Scenario 3D skill: make a fantasy lantern as a 3D model I can use in Blender, in my project Brand Studio.
updated: 2026-11-11
canonical: https://learn.scenario.com/mcp/what-is-scenario-mcp
---

Last updated: 2026-11-11

# What the Scenario MCP is, and how to connect it

> What the Scenario MCP does and when to use it, the exact setup for Claude, Cursor, VS Code, Codex and other clients, and Scenario's agent skills.

In short:

- The Scenario MCP lets your own AI agent run Scenario models, workflows and assets from a plain-language request, billed in the same credits as the web app.
- Add https://mcp.scenario.com/mcp to your AI client, sign in once in the browser, and confirm with a free request.
- Add Scenario's open-source skills so the agent follows tested procedures, and use the API instead for fixed, unattended code.


The Scenario MCP connects your own AI assistant to Scenario, so the assistant can pick a model, run it and bring the result back into the chat. This lesson shows what that looks like in Claude, adds a skill that turns one sentence into a 3D lantern you can open in Blender, then walks through the connection itself, step by step, and the same setup for Claude Code, Cursor, VS Code, Codex and other clients.

:::note As of November 2026
The models, settings and screens in this article are the ones Scenario offered in November 2026. New models and updates arrive often, so check the app for newer options before you choose.
:::

:::steps Quick version
1. Go to mcp.scenario.com, open **Installation**, pick your assistant and copy the address `https://mcp.scenario.com/mcp`.
2. In Claude, open **Customize** › **Connectors** › **Add** › **Add custom connector**, name it Scenario, paste the address and add it.
3. Click **Connect**, log in to Scenario and click **Authorize**.
4. Ask a free question, such as *"Can you see my Scenario project Brand Studio?"*, to check the connection.
5. Add skills for the jobs you do: upload a skill file in **Customize** › **Skills**, or install them with `npx skills add scenario-labs/skills` in a code tool.
:::

## Before you start

- **A Scenario account**, with a team and a project for the results. Everything the assistant makes lands in that project, next to what you made in the web app.
- **An AI assistant that can add remote tool servers.** The film uses Claude on claude.ai. Claude Code, Claude Desktop, Cursor, VS Code, Codex, Windsurf, Zed and others work too (see [Other assistants](#other-assistants)). On claude.ai, the Free, Pro and Max plans can each add a custom connector; on Team and Enterprise plans an owner adds it once for the whole organization.
- **Node.js**, only if you install skills from the command line.

Three ideas carry the whole lesson:

- **The Scenario MCP** is built on the Model Context Protocol, the open standard assistants use to call tools. It's a server at `https://mcp.scenario.com/mcp` that gives your assistant Scenario's tools: 99 of them, over more than 750 models, for images, video, 3D and audio.
- **You ask in plain words.** The assistant chooses the tools and the model; you review what comes back.
- **A skill** is a file of instructions for one kind of job: the steps, the rules and the checks. Your assistant reads it and follows it, so the job is done the tested way.

| Once connected, your assistant can | For example |
|---|---|
| Find and read models | Search more than 750 models, read their parameters, recommend one with reasons |
| Generate | Images, video, 3D and audio, then wait for the jobs |
| Show and file results | Display results in the chat, organize assets into collections |
| Work with your files and pipelines | Upload your files, run your team's workflows, check usage |

![An agent calls the Scenario MCP, which runs models on Scenario and saves the outputs in your project](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/877c805a9d57233a2fef4471819c4a21ef22b83bbde8b590a9aaaba8efacdb38.svg "The agent plans and calls tools; Scenario runs the models and keeps every output in your project.")

## Step 1: Ask your assistant for a picture

In the film, Claude is already connected (the connection itself starts at step 5 below). Open a new chat and type:

```text
Using Scenario, make a picture of a red fox curled up in the snow, in my project Brand Studio.
```

"Using Scenario" tells the assistant to use the Scenario tools rather than answer from its own knowledge, and naming the project tells it where to save the result. Claude picks a Scenario model, runs it and shows the image with **asset_display**. Its answer says what it made and how: here a 1536×1024 image with GPT Image 2.5 Sunburst at high quality, saved in Brand Studio, with a **View in Scenario** link that opens it in the web app.

![Claude's answer to the fox request: the asset_display call, a description of the image, the model used and a View in Scenario link](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/9436576fb875d8af151a5dc9df6c6e686f5865939c309740206cf5d411756218.webp)

**Used Scenario** above the answer opens the list of tool calls the assistant made, if you want to see the steps.

## Step 2: Understand what a skill adds

A skill makes the assistant much better at one kind of job. It's a folder with a `SKILL.md` file: a name, a description of when to use it, then the procedure. The film opens the `scenario-3d` skill in Scenario's open-source repository. Its description says to use it for 3D work through the Scenario MCP, and its overview gives the rule it follows: generate a concept image first, then run image-to-3D, which has a larger catalog and more art direction than text-to-3D.

![The SKILL.md file of the scenario-3d skill: its name, description and the start of its Scenario 3D Asset Workflows overview](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/761a220dc2fa300c96af4653c5e5ae4748d42b445616a65e72e6d9828519152d.webp)

## Step 3: Add the skill in Claude

In claude.ai, open **Customize**, stay on **Skills**, then click **Add** › **Upload skill**.

![The Customize page on Skills, with the Add menu open on Upload skill, Create a skill and Create with Claude](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/64406430fb539177eb61c37e46224ae4efc881b3a9c105aded1ee0c5febcd669.webp)

Choose the skill file, a `.zip` (here `scenario-3d-skill.zip`) or a `.md` file. The **Upload a skill** page checks the file before you add it:

- A `.md` file must contain the skill's name and description in YAML.
- A `.zip` or `.skill` file must include a `SKILL.md` file.
- **Preview** shows the name and description it read, and **Security scan** runs when you upload.

Click **Upload**. The skill is on, and Claude uses it whenever a request matches its description, or when you name it.

![The Upload a skill page with scenario-3d-skill.zip, the preview of the scenario-3d skill and the Upload button](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/38a881f34308124f5226cd6375defcd1e434bf04dc04c9d792c2a510592a02bf.webp)

## Step 4: Let the skill do a whole job

Start a new chat and name the skill in the request:

```text
Use the Scenario 3D skill: make a fantasy lantern as a 3D model I can use in Blender, in my project Brand Studio.
```

Claude follows the skill: it makes a concept image of the lantern first, turns it into a 3D model with an image-to-3D model, and saves both in Brand Studio. The concept appears in the chat as it goes.

![The lantern request in Claude and the concept image of an ornate brass lantern, shown with asset_display](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/fddbaccda4f0c694b31aebb0eda953d22e537082fec1f47ef06ad89ecd73a314.webp)

Download the model as a `.glb` file, then in Blender choose **File** › **Import** › **glTF 2.0 (.glb)**. The lantern arrives as separate named parts (frame, glass panes, flame, handle, roof), ready to place in a scene.

![The 3D lantern imported in Blender, with its parts listed in the outliner](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/34bac583315e0df9df9c1dccfab4621cf7d81e8001ce0d098a9c97777e9e86fb.webp)

A whole Blender project done this way is the next lesson, [Blender and the Scenario MCP, live](https://learn.scenario.com/mcp/first-session-with-scenario-mcp.md). First, the connection.

## Step 5: Copy the address from mcp.scenario.com

In a new browser tab, go to **mcp.scenario.com** and scroll to **Installation**. Keep **OAuth** selected (the recommended sign-in), pick the tab for your assistant, here **Claude.ai**, and click **Copy** next to `https://mcp.scenario.com/mcp`.

![The Installation section of mcp.scenario.com on the Claude.ai tab, with the server address copied](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/3ce2ce85415cb284e6d454da4e5d326499995fd951a44306b5c5e3b92e52ba02.webp)

The tab lists the same steps as below. It also covers the organization case: on Team or Enterprise, an owner (on Enterprise, also anyone whose custom role includes **Manage access to Libraries**) opens **Organization settings** › **Connectors** › **Add** › **Custom** › **Web** and pastes the URL. Each member then clicks **Connect** on it in **Customize** › **Connectors** and signs in with their own Scenario account; anyone else who tries to add it sees **Ask an organization owner**.

## Step 6: Add a custom connector in Claude

In claude.ai, open **Customize** › **Connectors**, then **Add** › **Add custom connector**. Type the name **Scenario** (it's how the connector shows in your list), paste the address in **MCP server URL** and click **Continue**.

![The Add custom connector dialog with the name Scenario and the URL https://mcp.scenario.com/mcp](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/4650bf35e13a719e4149278203dd0c1ede7a77b75e946b87a722b9dab638386c.webp)

Claude checks the server: it connects, looks up the sign-in settings and checks the sign-in provider. It then detects the right options for Scenario, so you don't change anything:

- **Authentication:** **Sign in now**, marked **Detected**. Each person signs in through Scenario's OAuth flow before using any tool.
- **OAuth client:** **Register automatically**, marked **Detected**.
- **Request headers:** leave empty. Headers are for API keys, which you don't need with OAuth.

Click **Add**.

![The second page of Add custom connector, with Sign in now and Register automatically both marked Detected](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/5d0bd88c69783c80213e82753c753d30662bdbf71a33b88b610181554715ca04.webp)

## Step 7: Connect and authorize

The connector page shows the address and a **Connect** button (until you finish, it says you started connecting but didn't finish). Click **Connect**. A Scenario page opens: **Claude wants access to Scenario**. Authorizing gives Claude the same access to Scenario that you have: running generations, browsing models and organizing your assets. It never sees your password. Click **Authorize**.

![The Scenario consent page listing what Claude asks for, with the Deny and Authorize buttons](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/67537d6671a4d53b81339abb826c9349e5352c14c09efc99d03d1f16d39e4ba6.webp)

You return to Claude, where the Scenario connector now lists its tools under **Tool permissions**, in groups such as **Interactive tools** and **Read-only tools**. Each tool has three choices: always allow, **Needs approval**, or never. With **Needs approval**, Claude asks before each call in Manual mode; in Auto mode, Claude checks each action for risks and pauses only on ones that look risky. Allow the read-only tools if the approvals slow you down. **Disconnect** removes the connection.

![The Scenario connector in Claude with its Tool permissions: Interactive tools and Read-only tools, each set to Needs approval](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/727465e5b52a444b88144e5ee513242090a295194963e8c18bdaef207ac6dd7c.webp)

## Step 8: Find more skills

Skills come from two places:

- **Scenario's open-source repository**, github.com/scenario-labs/skills. Its `skills` folder holds dozens of skills, one per job (3D, audio, ad variants, brand kits and more) and, under `dcc`, skills for Blender, Maya and ZBrush. Any of them can be uploaded the same way as in step 3.
- **Scenario's Explorations**, at scenario.com/explorations. Each Exploration is a real project shown step by step, and every Exploration has its skill to download, so you can make your own version.

![The skills folder of the scenario-labs/skills repository on GitHub, listing dcc, game-engines and the scenario skills](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/37d6c092b85f31121788e1ab1fd6ece185fe635ce2e5716f91de482d9d172e20.webp)

## Step 9: Check with a free question

Ask something that needs a Scenario tool but doesn't generate anything:

```text
Can you see my Scenario project Brand Studio?
```

A working connection answers from a tool call, here **Listed Scenario teams**, with your project and its team. Lookups like this are free. If Claude answers without a tool call, or asks you for a key, see [Common problems](#common-problems).

![Claude's answer after Listed Scenario teams: it can see Brand Studio in your team, then asks what to do there](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/eb72f55288db60364e2fa07ee4d46d722070f69efabc9a7dc1f42bb20a8a3342.webp)

## Other assistants

The steps are the same idea everywhere: add the URL, sign in once in the browser, then ask. The Installation section of mcp.scenario.com has a tab per assistant.

- **Claude Desktop:** custom connectors sync across every Claude surface, so a connector added on claude.ai is already there; on Team or Enterprise, click **Connect** on it in **Customize** › **Connectors**. Otherwise add it the same way: **Customize** › **Connectors** › **Add** › **Add custom connector**.
- **Claude Code:** the same applies if you sign in with the same Claude.ai account. Otherwise, run the command below; the OAuth sign-in opens on first use, and `/mcp` lets you sign in by hand.

![The Claude Code tab of the Installation section, with the claude mcp add command](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/38c22b0479c9bd063bf49be37d7c723c3a016f4b40ad306d440acfb540e8133c.webp)

| Client | Setup |
|---|---|
| Claude Code | `claude mcp add --transport http --scope user scenario https://mcp.scenario.com/mcp`; to sign in by hand, type `/mcp` and select **scenario** |
| Claude Desktop and claude.ai | **Customize** › **Connectors** › **Add** › **Add custom connector**, paste the URL |
| Cursor | **Settings**, **Tools & MCP**: `{ "mcpServers": { "scenario": { "url": "https://mcp.scenario.com/mcp" } } }` |
| VS Code | Command Palette, `MCP: Add Server`, **HTTP**, enter the URL; start it from `MCP: List Servers` |
| Codex | `codex mcp add scenario --url https://mcp.scenario.com/mcp`, or add it to `~/.codex/config.toml`; OAuth starts on first use |
| Gemini CLI | `gemini mcp add --scope user --transport http scenario https://mcp.scenario.com/mcp`, or add `{ "mcpServers": { "scenario": { "httpUrl": "https://mcp.scenario.com/mcp" } } }` to `~/.gemini/settings.json` (`httpUrl`, not `url`, which Gemini CLI reads as SSE); then `/mcp auth scenario` |
| Windsurf | Cascade, **Configure MCP**, the same `mcpServers` JSON as Cursor |
| Zed | `{ "context_servers": { "scenario": { "url": "https://mcp.scenario.com/mcp" } } }` |
| Amp | `amp mcp add scenario https://mcp.scenario.com/mcp` |
| ChatGPT | No Scenario-specific steps yet. If your plan lets you add a custom connector, paste the URL there |

If you can't add a custom connector, use the `mcp-remote` bridge (needs Node.js). In Claude Desktop, open **Settings** › **Developer** › **Edit Config**, add this entry to `claude_desktop_config.json`, then quit and restart the app:

```json
{ "mcpServers": { "scenario": {
  "command": "npx",
  "args": ["-y", "mcp-remote", "https://mcp.scenario.com/mcp"]
} } }
```

Prefer the native URL when a client offers both: the bridge is the usual cause of repeated sign-in prompts.

For skills in a code tool (Claude Code, Cursor, Codex, GitHub Copilot and other agents that read the open Agent Skills format), install them from the command line:

```sh
# The core skill: connecting, scoping, picking a model, generate and wait, errors
npx skills add scenario-labs/skills --skill scenario

# Choose more from a menu, then restart your agent
npx skills add scenario-labs/skills

# Update later
npx skills update
```

Start with `scenario`, then add the skills for the jobs you do: images, video, 3D, audio, game art, brand and formats, workflows, review or team administration, plus one skill per model family. The repository README lists bundles by goal and by role. Without installing anything, the agent can read the same skills from the server through `skill://scenario/<name>/SKILL.md` resources or the `skill_get` tool; served skills carry the text only, without bundled scripts.

## What a request looks like

Behind a sentence like *"Using Scenario, make a hero image of a ceramic teapot for a homeware shop, 3:2, pick a strong current model, show me the price first"*, the agent runs a loop of tool calls:

:::flow The agent loop for one image
Recommend | rank models, free |
Read schema | exact parameters | text
Quote | dry run, in CU |
Generate | run, then wait | image
Show | inline, with an app link | image
:::

1. `recommend` ranks models for the task by measured quality, speed and cost. It's free.
2. `model_schema_get` reads the chosen model's exact parameters.
3. `model_run` with `dry_run: true` quotes the cost in Compute Units (CU) and runs nothing.
4. `model_run` for real, then `jobs_wait` until the job finishes.
5. `asset_display` shows the result in the chat with a link to it in the web app.

Generations draw from the same team balance as the web app and the API; lookups such as `recommend` and `search` are free. Ask your agent to quote before any batch or video. An asset made in the web app can be handed to the agent by its ID (`asset_...`) to edit or build on, instead of starting over.

## When to use it

In the web app, you are the operator. With the Scenario MCP, the agent operates and you review. That pays off when:

- **The job has several steps.** "Restyle this concept three ways, I pick one, then animate it" is one request instead of three trips through three panels.
- **The job is repetitive.** An agent on your machine can read a folder of 40 product photos, upload them, run the same edit on each and file the results.
- **The job lives next to code or a 3D scene.** A developer in Cursor or Claude Code can ask for placeholder sprites and drop the files into the project; an artist can get a model ready to import in Blender.

Keep the web app for what needs your eyes and hands: comparing many takes side by side, painting a mask, training a model, building a workflow on the canvas.

| Surface | Who drives it | Best for |
|---|---|---|
| Web app | You | Exploring, reviewing, training, building workflows |
| [Scenario Agents](https://learn.scenario.com/agents/scenario-agents-overview.md) | Scenario Genie and the Node Agent, inside the web app | Help on the page you are on |
| Scenario MCP | Your own AI agent, outside the web app | Multi-step and repeated jobs from chat, IDE or terminal |
| [API](https://learn.scenario.com/browse#t-hc-api) | Your code | Production pipelines, apps, fixed integrations |

Use the Scenario MCP when a person is in the loop and the steps change from one request to the next. For fixed, unattended code that must run for months, use the API.

## OAuth or an API key

| | OAuth (recommended) | API key |
|---|---|---|
| How | The client opens a browser, you log in and click **Authorize** | A Base64 header built from a key and secret |
| Credentials in config files | None | Yes, treat the file as a secret |
| Acts as | You, with your team and project roles | The key, with its role and scopes |
| Saved instructions and memory, team admin actions | Yes | No |
| Use it for | Day-to-day work in an assistant or IDE | Headless runs, CI, shared machines |

For an API key, open **API Keys** in **Settings** › **Organization** and use a project key with the **Editor** or **Admin** role; a read-only key connects, then fails with `Forbidden` on the first generation ([API keys and authentication](https://learn.scenario.com/browse#t-hc-api)). Build the header value with `echo -n 'YOUR_API_KEY:YOUR_API_SECRET' | base64`, then add it to the client:

```sh
claude mcp add --transport http scenario https://mcp.scenario.com/mcp \
  --header "Authorization: Basic YOUR_BASE64_VALUE"
```

Clients with a JSON config take a `headers` entry next to the URL: `"headers": { "Authorization": "Basic YOUR_BASE64_VALUE" }`. **Never paste a key or secret** into a chat with your agent.

## Team, project and tools

Every call that touches content needs a team and a project. With one of each, the agent finds them; with several, the server doesn't guess and the agent asks you to pick. Outputs land in that project and its credits pay for them, so name it in the request ("in my project Brand Studio") or once per session: *"Use the team Design and the project Spring Campaign for everything today."* In long sessions the agent may ask again; restate the pair.

By default the server lists a core set of tools; the rest, such as collections, tagging, training and members, sit in a catalog the agent searches with `scenario_tools_search`. If your agent struggles with the catalog, connect to `https://mcp.scenario.com/mcp?toolsets=full` to list every tool, at the cost of more of the agent's context. The full live list is on mcp.scenario.com.

:::check
**Accept when:** the free question in step 9 comes back from a tool call with your team and project names, a request such as "recommend an image model for a product photo" returns ranked models, and a request that matches an installed skill follows its steps (concept first, then 3D, for the lantern).
**Reject when:** the assistant answers from memory without a tool call, asks you for an API key in the chat, reports an authentication error, or ignores a skill you installed.
:::

## Common problems

| What you see | What to do |
|---|---|
| No option to add a custom connector | On Team or Enterprise, an owner adds Scenario in **Organization settings** › **Connectors**; then click **Connect** on it. On other clients, use the `mcp-remote` bridge |
| "You started connecting to Scenario but didn't finish" | Click **Connect** again and finish with **Authorize** on the Scenario page |
| An authentication error after it worked before | Clear the stored sign-in and connect again: in Claude Code, `/mcp`, Scenario, **Clear authentication**; in Cursor, turn the server off and on. If it persists with the bridge, delete `~/.mcp-auth` and reconnect |
| Claude Desktop opens the browser on every message | Orphaned `mcp-remote` processes. Quit the app fully and restart, or use **Connectors** instead of the bridge |
| `Forbidden` when generating | Your API key is read-only, or your role in the project is below Contributor. Use an Editor or Admin key |
| The assistant asks which team or project to use | Expected when you have several. Pick one, and repeat the pair in later requests. Errors naming `context_missing` or `context_ambiguous` mean the same |
| The assistant asks before every tool call | Set the read-only tools to always allow in the connector's **Tool permissions**, or add them to your client's auto-approve list |
| The assistant doesn't use a skill you added | Check it's switched on in **Customize** › **Skills**, name it in the request, and in code tools restart the agent after installing |
| Anything else | Ask the assistant to "run Scenario diagnostics" (`diagnostics_run`). It names the failing layer and returns trace IDs to send to [support](https://learn.scenario.com/browse#help-center) |

## What's next

Put the connection and the skills to work on a full project in [Blender and the Scenario MCP, live](https://learn.scenario.com/mcp/first-session-with-scenario-mcp.md): two skills, a Blender blockout, a short film and a product ad, every prompt shown. For the agents built into the web app, see [Scenario Agents](https://learn.scenario.com/agents/scenario-agents-overview.md).

Source: https://learn.scenario.com/mcp/what-is-scenario-mcp