TolstoyMCP
Tolstoy MCP for AI-native ecommerce brands: Studio generates marketing videos and images, Library manages your media library, shoppable widgets, and ads, and Shopper searches products across brand stores with virtual try-on.
README
Tolstoy MCP
Connect any MCP client — Claude, ChatGPT, Cursor, Gemini, and more — to Tolstoy, the agentic platform for AI-native ecommerce brands. Run your shoppable video workspace right from chat: generate marketing content, manage your media library, build and publish shoppable widgets, tag products, and track ad performance.
Tolstoy exposes three remote MCP servers over Streamable HTTP. Studio and Library are secured with OAuth 2.1 + PKCE — no API keys to paste, your client runs the OAuth sign-in on first connect. Shopper is a public, no-auth marketplace server.
| Server | Endpoint | What it does |
|---|---|---|
| Tolstoy Studio | https://apilb.gotolstoy.com/mcp/v1/mcp |
Generate and iterate on marketing videos and images with Tolstoy Studio's AI creative director. |
| Tolstoy Library | https://apilb.gotolstoy.com/mcp/v1/library/mcp |
Run your shoppable video workspace — media library, shoppable widgets (Stories, Carousel, Spotlight), product tagging, multi-store, and Meta ads. |
| Tolstoy Shopper | https://apilb.gotolstoy.com/mcp/v1/shopper/mcp |
Shop across every brand store on Tolstoy — marketplace-wide product search, full product details, and virtual try-on. Public, no sign-in. |
Tools
Studio
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.
Library — media assets
list_assets— list your most recent library assets (videos, images, AI drafts).search_assets— search the library by query.get_asset— fetch full details for an asset, including tagged products and playlists.update_asset— rename an asset or toggle its favorite status.
Library — shoppable widgets
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.
Library — products & shoppability
search_products— find a store product by title to make videos shoppable.tag_video_product— tag (or untag) products on a video so it becomes shoppable in product-tagged playlists and PDP widgets.
Library — stores
list_stores— list the connected stores on your account; widget and product tools can target any of them.
Library — paid ads
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 (public marketplace — 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.
Connect
- In your MCP client, add a custom connector / remote MCP server.
- Paste the Studio, Library, or Shopper endpoint above.
- Sign in with your Tolstoy account when prompted (OAuth).
Per-client setup (Claude, ChatGPT, Cursor, Gemini CLI, Codex, Perplexity, Goose, Cherry Studio, and more) is available in the Tolstoy platform under Settings → MCP. The Tolstoy Library is also a published ChatGPT app — search "Tolstoy Library" in ChatGPT and click Connect.
Example client config
{
"mcpServers": {
"tolstoy-studio": { "url": "https://apilb.gotolstoy.com/mcp/v1/mcp" },
"tolstoy-library": { "url": "https://apilb.gotolstoy.com/mcp/v1/library/mcp" },
"tolstoy-shopper": { "url": "https://apilb.gotolstoy.com/mcp/v1/shopper/mcp" }
}
}
Codex CLI
codex mcp add targets STDIO servers, so add the remote server to ~/.codex/config.toml and run the OAuth login:
[mcp_servers.tolstoy-library]
url = "https://apilb.gotolstoy.com/mcp/v1/library/mcp"
[mcp_servers.tolstoy-studio]
url = "https://apilb.gotolstoy.com/mcp/v1/mcp"
[mcp_servers.tolstoy-shopper]
url = "https://apilb.gotolstoy.com/mcp/v1/shopper/mcp"
codex mcp login tolstoy-library
Authentication
OAuth 2.1 with PKCE, backed by Amazon Cognito. Discovery via RFC 9728 protected-resource metadata at each server's /.well-known endpoints. Each connection is bound to the Tolstoy workspace you authorize with. Shopper is a public marketplace server and requires no authentication.
Registry
Published in the official MCP Registry:
io.github.GoTolstoy/studioio.github.GoTolstoy/libraryio.github.GoTolstoy/shopper
The server.json for each is in registry/.
About
Tolstoy is the agentic platform for AI-native ecommerce brands, powering shoppable video for thousands of stores — https://www.gotolstoy.com
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.