Tolstoy MCP is most useful when it stops being a concept and starts becoming the control layer for real ecommerce work.

If your team already uses ChatGPT, Claude, Cursor, or Codex CLI, the setup path is short. Tolstoy’s public MCP docs already expose the endpoint, OAuth behavior, and first workflows you can run once the connection is live.

This guide is the practical follow-up to our broader explainer on what MCP means for ecommerce. Instead of defining the protocol again, it shows how to connect Tolstoy MCP to the AI client you already use and what to test first once you are in.

What you are connecting: one Tolstoy connection for all clients. In ChatGPT, use the published Tolstoy app.

The connection gives your AI client the Tolstoy agent, which creates media and does the work in your store, and your Library of videos and images. It is secured with OAuth 2.1 + PKCE, so there are no API keys to paste.

Why this setup matters for ecommerce teams

The point of connecting Tolstoy MCP is not to add another technical integration for its own sake. It is to let your AI client work inside the same systems your team already uses to create and ship commerce content.

According to Tolstoy’s official MCP overview, a connected client can create images and videos, find your media and products, and ask the Tolstoy agent to publish content and read performance right from chat. That changes the workflow from “AI gives me a suggestion” to “AI helps me move the work forward.”

For Shopify brands, that matters most when the bottleneck is operational: too many assets, too many surfaces, and too much copy-pasting between tools. Tolstoy MCP is useful because it turns that content layer into something an agent can act on.

What the Tolstoy connection includes

One connection carries everything. Your AI client finds what you have with a small set of tools, and hands the work to the Tolstoy agent:

  • finding videos and images in your Library, and uploading new files;
  • finding products in your store catalog, your saved fashion models, and your creative templates;
  • creating and revising images and videos with run_agent;
  • publishing media to your store, Meta Ads, Instagram, TikTok, and X; and
  • reading store, ad, and AI widget analytics, building AI widgets, and tagging products on videos.

If something is not available from chat, the agent gives you the Tolstoy platform page where you can do it.

How to connect Tolstoy MCP in ChatGPT

Use the published Tolstoy app in ChatGPT:

  1. Open the published Tolstoy app in ChatGPT.
  2. Follow the install or connect steps, sign in to Tolstoy, and approve access to your workspace.
  3. Start a conversation and ask ChatGPT to create content, or to work with your Library, products, or ads.

If your ChatGPT workspace restricts apps, ask your administrator to enable Tolstoy.

One connection gives ChatGPT access to everything available in your approved Tolstoy workspace.

How to connect Tolstoy MCP in Claude and Cursor

Claude and Cursor both support remote MCP connections, but the user experience differs slightly.

Claude

The official flow is straightforward:

  1. Open Settings → Connectors in Claude.
  2. Add a custom connector named Tolstoy.
  3. Paste the endpoint https://apilb.gotolstoy.com/mcp/v1/mcp and click Connect.

Once you sign in, Claude can call the same Tolstoy tools documented in the developer hub.

Cursor

Tolstoy’s docs keep the Cursor instructions intentionally short: add a remote MCP server in Cursor’s MCP settings with the Tolstoy endpoint, then let the first tool call open the OAuth sign-in tab.

That detail matters. Cursor does not need an API key here either. The first real MCP call triggers the Tolstoy login flow, and the connection is then tied to the Tolstoy workspace you authorized.

How to connect Tolstoy MCP in Codex CLI

Codex CLI is slightly different because Tolstoy’s docs note that codex mcp add targets STDIO servers, not remote HTTP servers. For Tolstoy MCP, you add the remote server directly in ~/.codex/config.toml, then run the OAuth login command.

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

Then log in:

codex mcp login tolstoy

The login opens a browser tab so you can sign in with your Tolstoy account. After that, the token is cached for future sessions.

If your team runs content workflows inside Codex already, this is the cleanest setup because it keeps Tolstoy inside the same CLI environment where you are planning and executing work.

What to do right after you connect

The best first test is one workflow that proves the connection is useful, not just technically valid:

  1. Search for the product you want to feature.
  2. Ask the Tolstoy agent for a product image or video of it.
  3. Revise the result once in the same chat.
  4. Find the new media in your Library, and ask the agent to publish it where you need it.

This is the fastest proof that the client can actually help with commerce execution, not just content lookup.

If you want that full loop in one platform, the public AI Studio and AI Player pages show where those outputs can go next.

Common setup mistakes to avoid

  • Expecting an API key flowTolstoy uses OAuth 2.1 + PKCE. If you are looking for a static key, you are following the wrong setup model.
  • Forgetting workspace scopeThe connection is bound to the Tolstoy workspace you authorize. Make sure you are signing into the correct account before testing.
  • Stopping after connectionA successful OAuth login is not the real milestone. Run one creation or publishing workflow immediately so the connector becomes part of work, not shelfware.

When to use Tolstoy MCP instead of a generic AI workflow

Use Tolstoy MCP when the job needs access to your real Tolstoy workspace: media, products, content creation, publishing, or ad-performance context.

Use a generic AI workflow when the job is still open-ended strategy, naming, messaging, or brainstorming. The handoff point is simple: once the task needs to touch the actual commerce system, connect Tolstoy MCP and move the work into tools.

That is also why this setup guide belongs alongside the broader Tolstoy MCP page. The page explains the platform story. The connection guide makes the platform usable inside the AI client your team already prefers.

Connect Tolstoy and run one real workflow. In ChatGPT, use the published Tolstoy app. If you are not in Tolstoy yet, get started free.

FAQs

Does Tolstoy MCP use API keys?

No. Tolstoy’s public docs specify OAuth 2.1 + PKCE for every MCP connection, so you sign in with your Tolstoy account instead of pasting an API key.

Can I connect Tolstoy MCP to ChatGPT?

Yes. Open the published Tolstoy app in ChatGPT, follow the install or connect steps, sign in to Tolstoy, and approve access to your workspace.

What can I do with my Library after connecting?

You can find your videos and images, read their details, upload new files, and find the products in your catalog. Ask the Tolstoy agent to tag products on videos or rename media.

What can the Tolstoy agent do after connecting?

It can create and revise images and videos, publish media to your store and ad channels, read store, ad and AI widget analytics, and build AI widgets, all from the same chat.

What is the first workflow worth testing?

A good first test is one end-to-end workflow: find a product, ask the Tolstoy agent for an image or video of it, then revise it once in the same chat.