GoodBarber Public Mcp

by goodbarber

316 downloads
Not rated
GitHub

About

Manage your GoodBarber app via natural language across eCommerce, Community, and Membership. Hosted MCP with OAuth — products, orders, promo codes, push broadcasts, customer subscriptions, traffic analytics. Connect from Claude Desktop, Cursor, VS Code, or any MCP-compatible clie

Details

Author
goodbarber
Downloads
316
Categories
Other, Automation, Developer Tools, Community

- Complete eCommerce toolset: products, orders, customers, promo codes, analytics
- Community engagement: push broadcasts, traffic data, device & OS metrics
- Membership management: active/expired/internal subscriptions, targeted push
- 85 union tools published in a standard MCP server card
- 30 ready‑to‑use natural‑language skills for instant use in clients

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name GoodBarber Public Mcp
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Configure the server in your MCP‑compatible client (e.g., Claude Desktop, Cursor, VS Code) using the npx command and the remote SSE endpoint: npx -y mcp-remote https://mcp.goodbarber.dev/mcp/sse. A connected session automatically shows a subset of the tool catalog (up to 85 tools) based on the app’s product families. Pre‑built natural‑language skills are also available from the goodbarber/goodbarber-skills repository.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "goodbarber public mcp": {
            "goodbarber-public-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "mcp-remote",
                    "https://mcp.goodbarber.dev/mcp/sse"
                ]
            }
        }
    }
}

McpServers

{
    "goodbarber-public-mcp": {
        "command": "npx",
        "args": [
            "-y",
            "mcp-remote",
            "https://mcp.goodbarber.dev/mcp/sse"
        ]
    }
}

Manage your GoodBarber eCommerce, Community, and Membership app via natural language.

44 AI-powered skills to manage your GoodBarber app with any MCP-compatible client — eCommerce, Community, Membership, and CMS.

These skills connect to theGoodBarber MCP serverand give your AI assistant structured workflows to manage your products, orders, customers, promotions, subscriptions, content, analytics, and more — all from a conversational interface.

Skills are instruction files (.md) that teach an AI assistanthowto perform specific tasks using your GoodBarber app's API via MCP (Model Context Protocol). Instead of manually calling API tools one by one, a skill orchestrates the full workflow — from data retrieval to formatted report — in a single natural-language request.

For example, asking"Show me my best sellers this month"triggers thebest-sellersskill, which automatically fetches your orders and catalog, computes rankings, and returns a formatted report.

You need to add the GoodBarber MCP server as acustom connectorin your client. The MCP server uses Server-Sent Events (SSE).

Replace<app_id>with your GoodBarber app ID if you manage multiple apps.

Authentication:the GoodBarber MCP server uses a browser-based OAuth flow.

When your MCP client connects to the SSE endpoint, it may open an authorization page onmcp.goodbarber.dev. On that page, you will be asked to paste yourGoodBarber Public API keyand validate the authorization. Generate your Public API key from your app's GoodBarber backoffice, on thePublic API / MCP serverpage.

- Donotopen the/authorizeURL manually in your browser.
- Start from the MCP client by connecting to the SSE endpoint.
- The client generates the full authorization request parameters automatically (redirect_uri,client_id,state,code_challenge, etc.).

If you open the authorization page manually without those parameters, the authentication will fail.
- OpenSettings > Connectors
- ClickAdd custom connector
- Enter the MCP server URL above
- The connector opens the GoodBarber authorization page — paste yourPublic API keythere and validate

# Single app claude mcp add goodbarber --transport sse https://mcp.goodbarber.dev/mcp/sse # Multiple apps claude mcp add goodbarber --transport sse https://mcp.goodbarber.dev/<app_id>/mcp/sse

Then start a Claude Code session — on the first GoodBarber tool call, the CLI will open the GoodBarber authorization page in your browser. Paste yourPublic API keythere and validate to complete the OAuth flow.

Add to your MCP configuration file (.cursor/mcp.json,.vscode/mcp.json, etc.):

{ "mcpServers": { "goodbarber": { "url": "https://mcp.goodbarber.dev/mcp/sse" } } }

The first connection from your client triggers the OAuth flow in your browser — paste yourPublic API keyon the GoodBarber authorization page and validate.

Point your client to the SSE endpoint above. The GoodBarber MCP server follows the standard MCP protocol and works with any compliant client.

Clone this repo and copy only the skills for your app type:

git clone https://github.com/goodbarber/goodbarber-skills.git

Note:the examples below use Claude's local skills directory (~/.claude/skills/). If you use another client, copy the skill folders to the directory expected by that client.

cp -r goodbarber-skills/skills/ecommerce/ ~/.claude/skills/
cp -r goodbarber-skills/skills/community/ ~/.claude/skills/
cp -r goodbarber-skills/skills/membership/ ~/.claude/skills/

CMS / Content (any app with content sections):

cp -r goodbarber-skills/skills/cms/ ~/.claude/skills/

Tip:CMS skills are cross-cutting — install them alongside any app type that has content sections (articles, agenda, maps, galleries, videos, sounds).

Tip:If your GoodBarber app combines multiple types (e.g. eCommerce + Membership), install skills from both directories.

Warning:some skill names are shared across app types (for exampleweekly-digest,traffic-report,push-broadcast, orpush-targeted). If you install skills from multiple directories into the same destination, rename them or place them in separate namespaces to avoid collisions.

Ask your AI assistant:"What skills do you have?"— it should list the installed GoodBarber skills.

Skills for managing editorial content — articles, agenda events, map points of interest, photo galleries, videos, and sounds. Work with any GoodBarber app that has CMS content sections.

Note:weekly-digest,traffic-report,push-broadcast, andpush-targetednames recur across app types. The CMS skills are namespaced by acms-prefix in their frontmatter (e.g.cms-weekly-digest) to avoid collisions — keep them in a separate folder if you install skills from multiple directories.

- Pagination-aware— Large datasets are filtered server-side, not blindly paginated
- Fuzzy matching— Mention a product or collection by name; the skill resolves it
- Workflow chaining— Every skill suggests 2–3 related skills to run next
- No destructive actions without confirmation— Mutations always require explicit user validation
- Structured output— Every skill returns a formatted report, not a one-liner

These skills work with any MCP-compatible AI client, including:

- Claude Desktop (Cowork)
- Claude Code (CLI)
- Cursor
- VS Code (Copilot, Claude, Cline, etc.)
- Windsurf
- Codex CLI
- Gemini CLI
- Any client supporting the Model Context Protocol

goodbarber-skills/ ├── README.md └── skills/ ├── ecommerce/ │ ├── best-sellers/SKILL.md │ ├── catalog-audit/SKILL.md │ ├── customer-insights/SKILL.md │ ├── ... │ ├── push-targeted/SKILL.md │ └── weekly-digest/SKILL.md ├── community/ │ ├── device-landscape/SKILL.md │ ├── push-broadcast/SKILL.md │ ├── push-targeted/SKILL.md │ ├── traffic-report/SKILL.md │ └── weekly-digest/SKILL.md ├── membership/ │ ├── subscription-audit/SKILL.md │ ├── expiration-calendar/SKILL.md │ ├── ... │ ├── push-broadcast/SKILL.md │ ├── push-targeted/SKILL.md │ └── weekly-digest/SKILL.md └── cms/ ├── article-publish/SKILL.md ├── content-audit/SKILL.md ├── editorial-calendar/SKILL.md ├── ... └── weekly-digest/SKILL.md

Want to add a skill? Create a folder inskills/<app-type>/with aSKILL.mdfile. Follow the existing format: YAML frontmatter (name,description,compatibility) + markdown instructions with tool workflow, input/output contracts, and guardrails.

The Unlicense— public domain, no restrictions.

D2C eCommerce fulfillment platform: manage orders, inventory, shipments, campaigns, and billing via AI agents

MCP server for meal delivery service. Browse menus, manage carts, confirm orders, skip/unskip deliveries, and view order history.

A Dsers MCP with 14 (and expanding) toolset to allow your agent to access and edit your dsers.

Automate AliExpress/Alibaba dropshipping product import to Shopify or Wix via DSers. Bulk import, pricing rules, multi-store push.

High-performance mobile automation architecture with a thin MCP gateway and dedicated Go workers for Android and iOS.

Unofficial Model Context Protocol server for iFood — browse, search, cart and order food via AI

Nas.com MCP Server lets AI agents connect to Nas.com so creators can create, launch, and sell with less manual work.

Remote MCP server for Packrift's AI-ready packaging catalog and ecommerce packaging workflows.

Pepesto gives your agent the ability to turn any recipe (a URL, plain text, or a photo) into a matched basket of real supermarket products with live prices, across 26 European supermarkets. The MCP covers the recipe → matched cart half of the grocery shopping workflow (parse / search / map ingredients to SKUs / check catalogs)

MCP server for Amazon shopping - AI agents can search products, check prices, add to cart, and manage shopping lists.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.