# Klevu (E-commerce AI Search) MCP for AI Agents AI Agent Connect

> Klevu (E-commerce AI Search) connects your AI agent to your product catalog. It lets you run keyword searches, audit merchandising rules, pull ML recommendations, and monitor trending products through a simple chat interface.

## Overview
- **Category:** ecommerce
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_upWpYwqu7xFl2Y0MdSXFTqA1KcNBDKyb7teJnJ7k/ai-agent-connect
- **Tags:** site-search, product-discovery, merchandising, ai-search, recommendation-engine, search-relevancy

## Description

Klevu (E-commerce AI Search) connects your account to any AI agent and lets you take full control of your e-commerce search foundation and product discovery through natural conversation. You can stop digging through complex dashboards or running manual API queries in Postman and just ask your agent to look into it. It lets you check how products are ranked in specific categories, see what's trending globally, or pull out specific segments using filters like size or brand. It's like having a merchandising expert who knows every corner of your catalog available at any time. Because Vinkius hosts this Connector, you can plug it into your existing workflow and get answers in seconds. Whether you're debugging a search relevancy issue or looking for data to back up a new merchandising strategy, you just talk to your agent and get the raw data or the high-level summary you need.

## Tools

### search_autocomplete
Fetch search autocomplete suggestions as the user types. This helps you understand what customers are looking for as they start typing.

### search_category
Retrieve products for a specific category page. Use this to audit your smart merchandising rules and display sequences.

### search_filtered
Search the Klevu catalog with specific facet filters applied. This lets you narrow down results by color, size, or brand.

### search_keyword
Search the catalog by keyword using Klevu AI. This is the primary way to check search relevancy for specific terms.

### search_pagination
Retrieve paginated results for a search query. Use this to see deeper results beyond the first page.

### search_product_id
Retrieve details for a specific catalog product by ID. This is perfect for looking up a single item's data quickly.

### search_raw
Execute a custom JSON search payload against the Klevu API. Use this for deeply nested query configurations or specific V2 settings.

### search_recs
Fetch Klevu AI product recommendations. This pulls visually similar, frequently bought together, or trending items.

### search_sorted
Perform a keyword search with a custom sorting order. This helps you see how different sorting rules affect your results.

### search_trending
View currently trending and most relevant global products. Use this to identify top-selling items and seasonal trends.

## Prompt Examples

**Prompt:** 
```
Search for 'waterproof jackets' in my Klevu catalog
```

**Response:** 
```
I've found 12 waterproof jackets. Top results include:

* **Summit Pro Hardshell**
* **RainGuard Trail Jacket**
* **Urban Explorer Parka**

Prices range from $89 to $245. Would you like to filter these by size or brand?
```

**Prompt:** 
```
Show me trending products for the 'Home Decor' category
```

**Response:** 
```
Retrieving trending items for 'Home Decor'...

**Current Top Sellers:**
1. Minimalist Ceramic Vase
2. Boho Woven Throw
3. Smart Ambient Lamp

These items are showing high engagement over the last 24 hours. Would you like to see visually similar items?
```

**Prompt:** 
```
Execute a filtered search for 'sneakers' with brand 'Nike'
```

**Response:** 
```
Filtering search for Nike sneakers...

**Found 8 matches:**
* Air Max Pulse
* Dunk Low Retro
* Zoom Fly 5

Would you like me to sort these by price from lowest to highest?
```

## Capabilities

### Execute keyword searches
Get high-relevancy results for any term in your catalog instantly.

### Audit category merchandising
See exactly which products appear in specific navigation paths.

### Filter product segments
Narrow down results by facets like brand, size, or color.

### Get autocomplete data
Pull the suggestions that appear as customers start typing.

### Fetch ML recommendations
Grab visually similar or frequently bought together items.

### Track trending products
Identify high-velocity items across your entire store.

### Execute raw API queries
Send custom JSON payloads for deeply nested query configurations.

## Use Cases

### Verify category rankings
A merchandiser needs to see if a new brand is showing up in the 'Shoes' category. They ask the agent to use search_category to verify the top 10 results.

### Test new search rules
A developer wants to test a new search rule. They use search_raw to send a specific JSON payload and see if the ranking changes.

### Identify seasonal trends
A data analyst wants to find the top 5 trending items in 'Home Decor'. They ask the agent to use search_trending and summarize the results.

### Analyze customer intent
A UX designer wants to see what people type for 'winter gear'. They use search_autocomplete to see the most common predicted terms.

## Benefits

- Stop manual API testing: Use search_keyword and search_raw to test search relevancy instantly without opening Postman.
- Faster merchandising audits: Use search_category to quickly see how products are ranked in different store views.
- Precise segment analysis: Use search_filtered to identify specific product groups by brand, size, or other facets.
- Better UX insights: Use search_autocomplete to see what your customers are actually looking for as they type.
- Data-driven trends: Use search_trending to spot seasonal shifts and high-velocity items across your store.
- Automated recommendations: Use search_recs to pull visually similar or frequently bought together items for your site.

## How It Works

The bottom line is you get a direct, conversational line to your Klevu data without touching a single line of code.

1. Subscribe to the Klevu (E-commerce AI Search) MCP on Vinkius.
2. Enter your Klevu Search URL and API Key in the configuration.
3. Start auditing your product discovery from Claude, Cursor, or any MCP-compatible client.

## Frequently Asked Questions

**Can I use the Klevu (E-commerce AI Search) MCP to check my category rankings?**
Yes, it lets you see exactly what products appear in specific navigation paths. You can audit your merchandising rules and display sequences through a natural conversation.

**How does the Klevu (E-commerce AI Search) MCP help with merchandising?**
It allows you to audit smart merchandising rules and see how products are ranked across different store views without having to click through every page manually.

**Can I use Klevu (E-commerce AI Search) MCP to find trending products?**
Yes, you can monitor global product velocity to identify top-selling items and seasonal trends across your entire store in real time.

**Does the Klevu (E-commerce AI Search) MCP support custom API queries?**
Yes, it includes a tool for custom JSON payloads, so you can execute deeply nested query configurations or specific V2 API settings directly.

**Can I use the Klevu (E-commerce AI Search) MCP to see autocomplete suggestions?**
Yes, it pulls the fast suggestions and popular matches based on partial search terms, helping you understand what customers are looking for as they type.

**Can the Klevu (E-commerce AI Search) MCP help with product recommendations?**
It can fetch Klevu AI product recommendations, including visually similar, frequently bought together, and trending items.

**Can I test how different filters affect search results through my agent?**
Yes. Use the `search_filtered` tool 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.

**How do I get AI product recommendations using natural language?**
The `search_recs` tool 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.

**Can I see which products are currently trending across my whole store?**
Absolutely. Use the `search_trending` tool 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.