Tolstoy Studio

by GoTolstoy

398 downloads
Not rated
GitHub

About

Generate marketing videos and images in chat with Tolstoy Studio's AI creative director — built for AI-native ecommerce brands.

Details

Author
GoTolstoy
Downloads
398
Categories
Productivity, Other, Marketing, Media, AI

- Generate marketing videos and images from prompts
- Iterate on previous generations in the same session
- OAuth 2.1 + PKCE authentication (no API keys)
- Works with Claude, ChatGPT, Cursor, Gemini, Perplexity, and more
- Remote MCP server via Streamable HTTP

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Tolstoy Studio
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Add Tolstoy Studio as a remote MCP server (Streamable HTTP) using the URL https://apilb.gotolstoy.com/mcp/v1/mcp. Sign in with your Tolstoy account via OAuth 2.1 + PKCE — no API keys to paste. Use the tools generate_studio_content (start a new generation) and iterate_studio_content (refine, animate, or vary). Full per-client setup is available in the Tolstoy platform under Settings → MCP.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "tolstoy studio": {
            "tolstoy-studio": {
                "url": "https://apilb.gotolstoy.com/mcp/v1/mcp"
            }
        }
    }
}

McpServers

{
    "tolstoy-studio": {
        "url": "https://apilb.gotolstoy.com/mcp/v1/mcp"
    }
}

Connect any MCP client — Claude, ChatGPT, Cursor, Gemini, and more — toTolstoy, the agentic platform for AI-native ecommerce brands. Run yourshoppable videoworkspace right from chat: generate marketing content, manage your media library, build and publish shoppable widgets, browse your catalog, tag products, and track ad performance.

Tolstoy exposes its remote MCP servers over Streamable HTTP. The mainTolstoyserver is secured with OAuth 2.1 + PKCE — no API keys to paste, your client runs the OAuth sign-in on first connect.Shopperis a separate public, no-auth marketplace server.

The mainTolstoyserver exposes the following tools.

- generate_studio_content— start a new Studio generation (image or video) from a prompt.
- iterate_studio_content— continue and refine an existing Studio generation in the same session.
- get_studio_session— check status and retrieve the finished media for a generation.
- list_studio_folders— list your Studio projects and folders.
- list_studio_chats— list the chats inside a Studio project or folder.

- list_assets— list your most recent library assets (videos, images, AI drafts).
- search_assets— search the library by name or creator handle.
- get_asset— fetch full details for an asset, including tagged products and playlists.
- update_asset— rename an asset or toggle its favorite status.

- list_widgets— list your onsite shoppable video widgets (Stories, Carousel, Spotlight, For You Feed, Tile, Collection Grid, Bubble Feed), live or draft.
- get_widget— inspect a widget: type, live status, content selection, and the actual videos it shows (per-product for PDP-mode shoppable widgets).
- create_widget— create a new shoppable widget from a template, with the platform's defaults.
- update_widget— rename, publish/unpublish, set PDP mode, or change a widget's content selection.

- list_collections— list the catalog collections for a connected store.
- search_products— find store products by title or query.
- browse_products— browse catalog products and collections for a connected store.
- tag_video_product— tag (or untag) products on a video so it becomes shoppable in product-tagged playlists and PDP widgets.

- list_stores— list the connected stores on your account; widget, catalog, and product tools can target any of them.

- list_ad_campaigns— list your Meta ad campaigns with real delivery status (effectiveStatustruth-telling).
- get_ads_performance— Meta ads performance: spend, ROAS, CTR, purchases — per campaign, ad set, or ad.
- publish_to_meta_ads_library— push a library video or image into Meta Ads Manager, ready for ad creation (no campaign, no spend).

Shopper(separate public marketplace server — no auth)

- search_products— search products across every brand store on Tolstoy, one marketplace-wide catalog.
- get_product— full product details: description, variants, price, media, the brand's videos, and buy/cart links.
- try_on— open an interactive virtual try-on of a product (participating brands); the shopper uploads a photo and sees themselves wearing the actual item.

App-aware clients (ChatGPT, Claude) also get interactive views — a shoppable-widget card grid and asset previews — rendered inline in chat.

Per-client setup (Claude, ChatGPT, Cursor, Gemini CLI, Codex, Perplexity, Goose, Cherry Studio, and more) is available in the Tolstoy platform underSettings → MCP.

This repository includes a Cursor plugin manifest in.cursor-plugin/plugin.json. Install the repository as a local plugin while developing, or install Tolstoy from the Cursor Marketplace after the listing is approved. The plugin adds the OAuth-secured Tolstoy workspace server. The public Tolstoy Shopper server remains available through the endpoint and client configuration documented above.

{ "mcpServers": { "tolstoy": { "url": "https://apilb.gotolstoy.com/mcp/v1/mcp" }, "tolstoy-shopper": { "url": "https://apilb.gotolstoy.com/mcp/v1/shopper/mcp" } } }

codex mcp addtargets STDIO servers, so add the remote server to~/.codex/config.tomland run the OAuth login:

[mcp_servers.tolstoy] url = "https://apilb.gotolstoy.com/mcp/v1/mcp" [mcp_servers.tolstoy-shopper] url = "https://apilb.gotolstoy.com/mcp/v1/shopper/mcp"

OAuth 2.1 with PKCE, backed by Amazon Cognito. Discovery via RFC 9728 protected-resource metadata at the server's/.well-knownendpoints. Each connection is bound to the Tolstoy workspace you authorize with.Shopperis a public marketplace server and requires no authentication.

- Privacy policy
-
Terms of use
- Support:
support@gotolstoy.com
- Security overview:
gotolstoy.com/security

Published in the officialMCP Registry:

- io.github.GoTolstoy/studio— the main Tolstoy server
- io.github.GoTolstoy/shopper

Theserver.jsonfor each is inregistry/.

Tolstoy is the agentic platform for AI-native ecommerce brands, powering shoppable video for thousands of stores —https://www.gotolstoy.com

-

Vidoly AI – AI Image & Video Generator

Use Vidoly AI to generate images, create videos, and streamline visual production. Explore AI-powered creative tools for social media, branding, ecommerce, and digital content.

Generate on-brand image and video ads straight from your prompts.

34-tool MCP server for CutPro's v1 API — analyze videos, clip, render, and publish posts via AI clients like Claude, ChatGPT, and Cursor.

Run reusable AI creative workflows for ecommerce product photography, UGC ads, image-to-video, text-to-video, asset uploads, and async generation results.

Render videos from JSON via the iLoveVideoEditor cloud API: motion-design templates, GPU effects, transitions, batch rendering, webhooks.

The World's First AI Music MCP Beyond images and video, your agent can now generate music.

AVCLabs MCP integrates AI-powered video upscaling, quality enhancement, and SAM3 image segmentation into MCP workflows. It enhances low-resolution videos, cleans noisy footage, and extracts target objects through text prompts.

Enables AI assistants to interact with DaVinci Resolve Studio for advanced control over video editing, color grading, and audio.

An MCP server integration for the DaVinci Resolve video editing software.

Fashion vertical MCP server — SEO audits, trend analysis, competitor monitoring, and ad copy generation for fashion e-commerce. Includes 12 playbook skills for AI agents.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.