Connect AI tools over MCP

MixShift exposes an MCP (Model Context Protocol) server, so AI tools can query your warehouse, look at live Amazon data, and read your brand context from inside their own chat. Any current MCP client connects over streamable HTTP at https://mcp.mixshift.io/mcp.

One distinction worth knowing up front: the MixShift AI plugin for Claude bundles skills and a CLI on top of this connection. Every other client below gets the data connection itself, which is already a lot: tables, live Amazon operations, the timeline, and brand context as tools the model can call, including the ones that make changes (see below for which connections can use them).

Claude (claude.ai and Claude Desktop)

Add a custom connector pointed at https://mcp.mixshift.io/mcp and sign in when prompted. Claude handles the OAuth flow; there is no token to paste. The connector gets the same access as the MixShift plugin, including the tools that make changes, and the consent screen says so before you approve. If you added the connector before September 27, remove it and add it again to get this access. If you use Claude Code or Cowork, skip the connector and install the plugin instead; it is the better experience there.

ChatGPT

Turn on developer mode in ChatGPT's settings, then add MixShift as a custom app with the server URL https://mcp.mixshift.io/mcp and OAuth, and sign in when prompted. ChatGPT registers itself; there is no token to paste. The app gets the same access as the MixShift plugin, including the tools that make changes. If you added MixShift to ChatGPT before September 27, add it again to get the full access: reconnecting keeps the access it was first set up with.

Cursor

Cursor takes a static token. Get one from mcp.mixshift.io/login?mode=direct, then add the server to .cursor/mcp.json with the token in the Authorization: Bearer header. Sessions are long-lived; refresh the token when a request comes back unauthorized.

Codex

Same pattern as Cursor: token from mcp.mixshift.io/login?mode=direct, configured in ~/.codex/config.toml. Codex requires the streamable HTTP transport, which is exactly what the endpoint speaks.

Unattended connections

Automations and servers should mint tokens from a service credential rather than a personal login. See Get access.

What the tools can do once connected

List and describe warehouse tables, and run read-only SQL.
Call cataloged live Amazon operations (retail and advertising).
Read and add to your brand change log, record and corroborate stakes, read brand context documents, and retire or restore a brand your team no longer works on. See Work with brand memory.

Each tool call checks its own permission scope, so a read-only credential simply cannot invoke a write, no matter what the model asks for.

Which of these a connection can use depends on the scopes its token holds. A Claude (claude.ai and Claude Desktop) connector, MixShift added to ChatGPT as a custom app, and a token from mcp.mixshift.io/login?mode=direct (the Cursor and Codex setup above) are your own sign-in, so they hold the same scopes as the MixShift plugin: every read, plus Ads and listing changes, adding to the change log, and retiring or restoring a brand. Those changes keep the plugin's safety rails: an Ads write defaults to a dry-run preview and is audit-logged, and a listing change previews first and commits only the exact change set you approved. A Claude connector you added before September 27 keeps the read-only access it was approved with (its consent screen said read-only): remove it and add it again to get the full set. If you added MixShift to ChatGPT before September 27, add it again to get the full access: reconnecting keeps the access it was first set up with. Service credentials and partner apps hold only the scopes granted to them.