An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Klevu E Commerce AI Search to ChatGPT and Claude

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 your entire product catalog through natural conversation.

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 · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Klevu.

  1. 01

    Search category

    This capability retrieves products for a specific category page using Klevu Smart Category Merchandising.

  2. 02

    Search filtered

    Use this to search the Klevu catalog while applying specific facets like color, size, or brand.

  3. 03

    Search keyword

    This capability performs keyword searches against your catalog using Klevu AI.

  4. 04

    Search product ID

    Get specific details for a single catalog item by providing its product ID.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Klevu.

  1. 05

    Search recs

    This capability fetches product recommendations generated by Klevu AI.

  2. 06

    Search trending

    Access a list of products that are currently trending or globally relevant.

  3. 07

    Search autocomplete

    Retrieve autocomplete suggestions based on partial search terms.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Klevu.

  1. 08

    Search pagination

    This capability pulls paginated results for a specific search query.

  2. 09

    Search raw

    Execute custom JSON search payloads against the Klevu API for deep query configurations.

  3. 10

    Search sorted

    Run keyword searches that apply a custom sorting order to the results.

Real work

What teams actually run

01

Search Testing

A developer asks the agent to verify how a specific keyword performs against the catalog.

02

Merchandising Checks

A merchandiser checks if specific products are appearing correctly in a category path.

03

Trend Analysis

An analyst pulls trending product data to see what is gaining velocity.

04

UX Auditing

A team checks autocomplete suggestions to ensure they match user intent.

Automate a task

Put Klevu 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

Klevu 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 Klevu 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

933ms average. Fast in production.

Klevu is checked daily against the live service.

Daily averagePeak 1148ms
Oct 3Today
Fastest day
776ms
Slowest day
1148ms
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. 10 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 Klevu, so you can see the experience inside your AI.

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

Klevu Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_upWpYwqu7xFl2Y0MdSXFTqA1KcNBDKyb7teJnJ7k/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 — Klevu capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "klevu-e-commerce-ai-search-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_upWpYwqu7xFl2Y0MdSXFTqA1KcNBDKyb7teJnJ7k/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 Klevu in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Klevu owners hand off.

This MCP is built for professionals managing e-commerce discovery and search relevance.

  • 01

    E-commerce Developers

    They use the agent to test search relevance and API results without manual queries.

  • 02

    Digital Merchandisers

    They audit product rankings and recommendation logic across different store views.

  • 03

    Data Analysts

    They monitor search performance and trending products to find catalog gaps.

FAQ

Questions Klevu owners ask.

  • 01

    How do I connect my Klevu account?

    You subscribe to the MCP on Vinkius and enter your Klevu Search URL and API Key. Once connected, it is ready to use in your AI client.

  • 02

    Which AI clients can I use with this MCP?

    You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can I run custom API calls?

    Yes, the search_raw capability allows you to execute custom JSON search payloads for specific V2 API settings.

  • 04

    Does this replace my Klevu dashboard?

    It acts as a conversational interface for your Klevu data, making it easier to audit and test search results without using the dashboard or manual API capabilities.

  • 05

    Can I see what products are trending?

    Yes, you can use the search_trending capability to view products with high global velocity and relevance.

  • 06

    Can I test how different filters affect search results through my agent?

    Yes. Use the search_filtered capability by providing a query and specific facet values (e.g., 'color': 'red'). Your agent will return the filtered result set, allowing you to verify that your indexing and category mappings are working correctly.

  • 07

    How do I get AI product recommendations using natural language?

    The search_recs capability allows your agent to fetch product recommendations based on specific ML logics, such as visual similarity or trending items. Simply ask your agent to show recommendations for a specific context or logic path.

  • 08

    Can I see which products are currently trending across my whole store?

    Absolutely. Use the search_trending capability to retrieve a baseline query sorted by relevance and sales velocity. Your agent will return the most popular items across your entire catalog, helping you monitor seasonal trends in real-time.

Explore

More in Ecommerce

Suggestions

Connect Klevu to Claude, Cursor, ChatGPT & more