How do I connect my Constructor.io account?

You just need your Constructor.io Public API Key, which you can find in your dashboard under Integration. Once you enter it in Vinkius, you can connect your AI client immediately.

Which AI clients can I use with this MCP?

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

Can I test my site's autocomplete with this?

Yes, the autocomplete capability allows your agent to perform structural extraction of the properties that drive your predictive typing.

Does this work with my existing recommendation pods?

Yes, the get_recommendations capability lets you pull products directly from your custom recommendation pods.

Is this for developers or marketers?

It is for both. Developers can use it to debug API parameters, while marketers can use it to verify that curated collections are appearing correctly.

Can my agent check the ML ranking for a specific product search?

Yes. Use the 'search_products' capability. The agent will retrieve results ranked by Constructor's ML engine, allowing you to audit how products are surfaced based on specific keywords and intent signals.

How do I retrieve personalized recommendations via the agent?

Provide the 'pod_id' to your agent and use the 'get_recommendations' capability. The agent will query the collaborative filtering models to return a list of products tailored to your specified recommendation logic.

Can I test attribute filtering like color or size through chat?

Absolutely. The 'search_filtered' capability allows you to pass exact attribute mappings (e.g., 'color:blue,size:L'). Your agent will verify how the API restricts results to those specific structural bounds.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Constructor 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. Control site search and product rankings 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.

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.

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 Constructor.

01
Browse brand
This capability lets you inspect internal brand arrays to verify how specific manufacturers are categorized.
02
Browse collection
Use this to identify active product collections and verify their contents.
03
Get recommendations
This capability retrieves specific product recommendations from your existing recommendation pods.
04
Search pagination
This capability handles automated validation checks for paginated search results.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Constructor.

05
Search products
Use this to find specific product records within the Constructor.io platform.
06
Autocomplete
This capability extracts the structural properties that drive your site's predictive typing and autocomplete logic.
07
Custom search
This capability executes specialized search queries using custom parsing logic.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Constructor.

08
Search filtered
Use this to run searches that apply strict attribute filters like color, size, or specific features.
09
Search sorted
This capability allows you to test search results against specific sorting rules.
10
Browse category
This capability lets you navigate through your product category hierarchy and JSON payloads.

Real work

What teams actually run

Search Ranking Audits

Check if your top ML-ranked products match your intended business logic.

Filter Logic Testing

Verify that size and color filters return the correct product sets.

Recommendation Verification

Ensure that specific recommendation pods are surfacing the right items to users.

Taxonomy Validation

Confirm that brand and category hierarchies are correctly structured.

Automate a task

Put Constructor 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

Constructor 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.

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

You don't need a client to put Constructor 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.

Constructor is checked daily against the live service.

Daily averagePeak 1265ms

Oct 3Today

Fastest day: 773ms
Slowest day: 1265ms
14-day trend: Improving-7%

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 Constructor, so you can see the experience inside your AI.

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

Constructor Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_7QdndEEXMElkrXV72k1k9X9VY0HS8rfUr6VIhrH5/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Constructor capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "constructor-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_7QdndEEXMElkrXV72k1k9X9VY0HS8rfUr6VIhrH5/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 Constructor in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Constructor owners hand off.

This MCP is built for e-commerce professionals who need to audit and test discovery logic without manual dashboard navigation.

01
E-commerce Managers
They use the AI to audit search rankings and recommendation pods.
02
Product Owners
They monitor category browsing and verify attribute filtering logic.
03
Developers
They test and debug search API parameters and recommendation outputs.
04
Marketing Teams
They verify that curated collections and brand taxonomies are correctly mapped.

FAQ

Questions Constructor owners ask.

01
How do I connect my Constructor.io account?
You just need your Constructor.io Public API Key, which you can find in your dashboard under Integration. Once you enter it in Vinkius, you can connect your AI client immediately.
02
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
03
Can I test my site's autocomplete with this?
Yes, the autocomplete capability allows your agent to perform structural extraction of the properties that drive your predictive typing.
04
Does this work with my existing recommendation pods?
Yes, the get_recommendations capability lets you pull products directly from your custom recommendation pods.
05
Is this for developers or marketers?
It is for both. Developers can use it to debug API parameters, while marketers can use it to verify that curated collections are appearing correctly.
06
Can my agent check the ML ranking for a specific product search?
Yes. Use the 'search_products' capability. The agent will retrieve results ranked by Constructor's ML engine, allowing you to audit how products are surfaced based on specific keywords and intent signals.
07
How do I retrieve personalized recommendations via the agent?
Provide the 'pod_id' to your agent and use the 'get_recommendations' capability. The agent will query the collaborative filtering models to return a list of products tailored to your specified recommendation logic.
08
Can I test attribute filtering like color or size through chat?
Absolutely. The 'search_filtered' capability allows you to pass exact attribute mappings (e.g., 'color:blue,size:L'). Your agent will verify how the API restricts results to those specific structural bounds.

Explore

More in Ecommerce

Connect Constructor to Claude, Cursor, ChatGPT & more

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

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Browse brand

Browse collection

Get recommendations

Search pagination

05-07

Search products

Autocomplete

Custom search

08-10

Search filtered

Search sorted

Browse category

What teams actually run

Search Ranking Audits

Filter Logic Testing

Recommendation Verification

Taxonomy Validation

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

Constructor Connector

Claude Desktop

E-commerce Managers

Product Owners

Developers

Marketing Teams

How do I connect my Constructor.io account?

Which AI clients can I use with this MCP?

Can I test my site's autocomplete with this?

Does this work with my existing recommendation pods?

Is this for developers or marketers?

Can my agent check the ML ranking for a specific product search?

How do I retrieve personalized recommendations via the agent?

Can I test attribute filtering like color or size through chat?

Klevu (E-commerce AI Search) AI Connector

Searchspring AI Connector

Lucidworks Fusion (AI Search & Discovery) AI Connector

Doofinder AI Connector

Suggestions

AddSearch AI Connector

Product Discovery Prover AI Connector

Product-Market Fit Score Engine AI Connector

Product-Market Fit Diagnostic Engine AI Connector