# FeedShine MCP server

> Review and change Shopify product feeds for Google Shopping, Meta, TikTok and more by asking your AI assistant.

- Listing: https://mcp.tc/i/feedshine
- Connect: use the server's own URL `https://feedshine.app/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [E-commerce](https://mcp.tc/c/ecommerce)
- Vendor: Digital Darts
- Homepage: <https://feedshine.app/>

## About

FeedShine builds product feeds from a Shopify store for Google Shopping, Meta, Microsoft, Pinterest, TikTok, Snapchat, Criteo and AppLovin. Through this server an assistant can review feed settings, preview products, adjust attributes and run a feed. Changes are not saved until the user approves them.

It runs as a hosted remote endpoint over streamable HTTP. A connection is approved with a one-time connect code generated in the FeedShine app settings, which expires after 10 minutes and ties the connection to the Shopify store. The FeedShine Shopify app must be installed.

## What it can do

- Review feed settings for a Shopify store
- Preview products as they appear in a feed
- Adjust feed attributes across many products
- Run a feed rebuild
- Approve changes before they are saved

## Example prompts

- "Which products are missing a Google category in my feed?"
- "Preview how my Trail Runner product appears in the Google feed"
- "Set the Google category for all products missing one"
- "Run my Google Shopping feed now"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http feedshine https://feedshine.app/mcp
```

2. Start Claude Code, type `/mcp`, pick **feedshine** and choose **Authenticate**. A browser window opens for the Digital Darts sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **FeedShine** and paste this URL:

```url
https://feedshine.app/mcp
```

3. Click **Add**, then **Connect**, and sign in when Digital Darts asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=FeedShine&connectorUrl=https%3A%2F%2Ffeedshine.app%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://feedshine.app/mcp` and click **Add**.

3. Click **Connect** and sign in when Digital Darts asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://feedshine.app/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Digital Darts to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=feedshine&config=eyJ1cmwiOiJodHRwczovL2ZlZWRzaGluZS5hcHAvbWNwIn0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "feedshine": {
      "url": "https://feedshine.app/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=feedshine&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Ffeedshine.app%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"feedshine","type":"http","url":"https://feedshine.app/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "feedshine": {
      "type": "http",
      "url": "https://feedshine.app/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "feedshine": {
      "serverUrl": "https://feedshine.app/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add feedshine --url https://feedshine.app/mcp
codex mcp login feedshine
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.feedshine]
url = "https://feedshine.app/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http feedshine https://feedshine.app/mcp
```

Then, inside Gemini CLI, run `/mcp auth feedshine` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "feedshine": {
      "type": "http",
      "url": "https://feedshine.app/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://feedshine.app/mcp`.

## Details

- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-10-27
- Updated: 2026-10-27

---
Source: https://mcp.tc/i/feedshine (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
