An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Narvar to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage the entire post-purchase journey through a single chat interface.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 5 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 5 available through Narvar.

  1. 01

    Get tracking

    This capability pulls real-time tracking updates and event history for any specific carrier tracking number.

  2. 02

    Get order

    Use this to pull full order details, including specific line items and current fulfillment status.

  3. 03

    Get estimated delivery dates

    This capability calculates precise estimated delivery dates to help you optimize your checkout experience.

Capability set02 / 02

04-05

2 capabilities in this set.

Part of 5 available through Narvar.

  1. 04

    Create return

    This capability initiates return requests for orders and handles the generation of return labels.

  2. 05

    Trigger notification

    Use this to send transactional email or SMS updates to customers regarding their shipment milestones.

Real work

What teams actually run

01

Instant Order Tracking

A support agent asks the AI for a status update to answer a customer inquiry immediately.

02

Self-Service Returns

The AI processes a return request and generates a label without human intervention.

03

Proactive Notifications

The agent triggers a shipment milestone alert to keep customers informed.

04

Checkout Optimization

Logistics teams use the agent to get accurate delivery estimates for the storefront.

Automate a task

Put Narvar to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Narvar works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Narvar to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1018ms average. Fast in production.

Narvar is checked daily against the live service.

Daily averagePeak 1498ms
Oct 3Today
Fastest day
777ms
Slowest day
1498ms
14-day trend
Stable0%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 5 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Narvar, so you can see the experience inside your AI.

It does not authenticate your account with Narvar. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Narvar Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_T6sDqYpxjUH72Oer0q6gGL8QVeEZuTZrLqNFnX3h/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Narvar capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "narvar-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_T6sDqYpxjUH72Oer0q6gGL8QVeEZuTZrLqNFnX3h/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Narvar in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Narvar owners hand off.

This MCP is built for teams managing high-volume e-commerce logistics and customer service.

  • 01

    E-commerce Managers

    They use the agent to monitor shipment health and fulfillment across different carriers.

  • 02

    Customer Support Teams

    They hand off 'where is my order' queries and return processing to the AI.

  • 03

    Logistics Operations

    They use the agent to analyze delivery performance and send delay alerts.

FAQ

Questions Narvar owners ask.

  • 01

    How do I connect Narvar to my AI client?

    You subscribe to the MCP on Vinkius and enter your Narvar API Key. Once connected, you can use it in any MCP-compatible client like Claude or Cursor.

  • 02

    Can this MCP handle return labels?

    Yes, the create_return capability allows your agent to initiate return requests and generate labels.

  • 03

    Which carriers are supported?

    The MCP uses Narvar's existing carrier integrations to pull real-time tracking data for any supported carrier.

  • 04

    Can I send emails through this MCP?

    Yes, you can use the trigger_notification capability to send transactional email or SMS updates to customers.

  • 05

    Do I need to use a specific AI model?

    No, this works with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 06

    Can I track a package without knowing the carrier?

    Yes, although providing the carrier helps accuracy. Use get_tracking with the tracking number, and the system will attempt to retrieve the latest events from Narvar's network.

  • 07

    How do I generate a return label for a customer?

    Use the create_return capability. You will need to provide the order number, customer details, and the items being returned. The agent will then initiate the return flow in Narvar.

  • 08

    Can I get delivery estimates before an order is placed?

    Absolutely. Use the get_estimated_delivery_dates capability by providing the origin, destination, and items. This is perfect for showing accurate shipping times during checkout.

Explore

More in Ecommerce

Suggestions

Connect Narvar to Claude, Cursor, ChatGPT & more