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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。