MartechDB
MartechDB
Toggle sidebar

Kealabs MCP server

kealabs.com

Yes. Kealabs publishes an official MCP server at https://mcp.kealabs.com/mcp. It's hosted. It offers 5 tools. We last checked it on 22 Nov 2026.

Official MCP server
Hosted
Sign-in: see vendor docs

Official: answers MCP requests at mcp.kealabs.com, on Kealabs's own domain kealabs.com. Checked 22 Nov 2026. Maintained by Stuart Brameld.

Key facts

As of 22 Nov 2026, Kealabs's official MCP server scores 55/100 (provisional) on MartechDB's Agent Readiness Index (v1.1). It answered 54 of our 55 checks in the last 90 days and lists 5 tools.

How the Agent Readiness Index works · Wrong? Suggest a correction

Kealabs MCP server review

55/100

Kealabs's MCP server scores 55/100 on MartechDB's Agent Readiness Index: usable by AI agents, with gaps.

The good

  • Hosted by Kealabs: connect by URL, with nothing to install

The bad

  • Access goes through sales

Not checked yet: how you sign in; a docs page listing its tools. Anything not checked scores nothing.

Official MCP server

Kealabs MCP server

Address
https://mcp.kealabs.com/mcp
Runs
Hosted
Sign-in
Sign-in: see vendor docs
Cost to use
Through sales
Official MCP Registry
Not listed
How we know it's official
  • Answers MCP requests at mcp.kealabs.com, on Kealabs's own domain kealabs.com.
Checked 22 Nov 2026.
Tools
5 tools · listed 22 Nov 2026
First seen
1 Oct 2026
Last checked
Reachable ·
16 Nov 2026: reachable
17 Nov 2026: reachable
18 Nov 2026: reachable
19 Nov 2026: reachable
20 Nov 2026: reachable
21 Nov 2026: reachable
22 Nov 2026: reachable
Uptime
98.2% · 54 of 55 checks reachable since 1 Oct 2026

Kealabs MCP server tools (5)

As the server lists them. Names and descriptions are the vendor's own.

  • kea_search

    Full-text product search via Kea Labs. Requires shop token (ShopID/public token). How to use: 1) Start broad: call with q only. 2) Inspect response.facets. Each facet has key, type, and values/stats. 3) To refine, call again WITH THE SAME requestId and apply facets as filters/ranges: - Discrete facet: filters = { "<facet.key>": ["<value1>", "<value2>"] } - Numeric facet: ranges = { "<facet.key>": { "min": x, "max": y } } 4) Never invent facet keys; always reuse keys returned in facets. Empty q is valid: it returns popular products, or can be used with category/filters. Sorting examples: relevance, priceup, pricedown, abcup, abcdown, saledown, newest. If meta.warn is present (ALL_FAILED, FORCE_FUZZY, FALLBACK_OR, NO_DELIVERY_ZONE_FOUND), explain it to the user.

  • kea_visual_search

    Visual (image-based) search via Kea Labs. Requires shop token (ShopID/public token) and imageBase64. How to use: 1) Provide imageBase64 (a full image encoded as base64). Optionally add q for hybrid search. 2) Inspect facets in the response. 3) Refine iteratively using the SAME requestId and applying facets as filters/ranges. 4) Keep q empty for pure visual similarity; add q to bias results. visualThreshold adjusts similarity strictness (0.5..0.99, default ~0.9). Sorting examples: relevance, priceup, pricedown, abcup, abcdown, saledown, newest.

  • kea_recommend_similar

    Get similar products via Kea Labs recommendations. Requires shop token (ShopID) and productId from search results.

  • kea_recommend_feed

    Recommendation feed (infinite scroll) via Kea Labs Feed API. Requires shop token (ShopID/public token). Core idea: - The API returns a feedId. Reuse the same feedId in the next call to get the next portion of items. - If feedId is not provided, a new feed is started. Scenarios: 1) Tracking-based personalization: call with token only. 2) Explicit product interests: pass positiveInterestIds / negativeInterestIds / purchasedInterestIds. 3) Semantic interests: pass positiveInterestStrings (interests) and/or negativeInterestStrings. Use ignoreCartData=true when you want the feed to rely ONLY on explicit interests. Notes: - diversify=true (default) makes the feed less repetitive. - cartId can be omitted; the service may generate identifiers automatically.

  • kea_recommend_models

    List available recommendation models/algorithms for the current shop. Requires shop token (ShopID).

Connect your AI to Kealabs

Add the official Kealabs MCP server to Claude, ChatGPT or your editor.

Connect Kealabs MCP to Claude

Claude.ai and Claude Desktop

  1. Open Customize, then Connectors.

  2. Click +, then Add custom connector.

  3. Name it Kealabs, paste the address below and click Add.

Claude Code

Kealabs MCP server questions

Does Kealabs have an official MCP server?

Yes. Kealabs publishes its MCP server itself. Its address is on Kealabs's own domain (mcp.kealabs.com). MartechDB only lists servers a vendor publishes, never community copies.

What is the Kealabs MCP server URL?

The address is https://mcp.kealabs.com/mcp.

How do I connect Kealabs MCP to Claude, ChatGPT or Cursor?

In Claude, add https://mcp.kealabs.com/mcp as a custom connector (Customize, Connectors, Add custom connector). In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http kealabs https://mcp.kealabs.com/mcp

What can the Kealabs MCP server do?

It offers 5 tools: kea_search, kea_visual_search, kea_recommend_similar, kea_recommend_feed and kea_recommend_models (as listed on 22 Nov 2026).

Is the Kealabs MCP server in the official MCP Registry?

No. Kealabs hasn't published it to the official MCP Registry.

Is the Kealabs MCP server working?

Yes. It answered our most recent check. We last checked it on 22 Nov 2026.

What are the alternatives to Kealabs's MCP server?

In Testing & personalisation, the most agent-friendly alternatives with an official MCP server are Unbounce (100/100), LaunchDarkly (97/100), PostHog (97/100), Userbrain (97/100) and Leadpages (95/100). Kealabs scores 55/100 on the same index.

Alternatives to Kealabs's MCP server

Vendors in Testing & personalisation with an official MCP server, the most agent-friendly first. Kealabs scores 55/100.

Compare all 55 Testing & personalisation vendors →

Use with AI

Connect your AI to MartechDB

Then ask it about Kealabs, or any of the 1,850 marketing tools with an official MCP server. Free, no sign-in.

Claude.ai and Claude Desktop

  1. Open Customize, then Connectors.

  2. Click +, then Add custom connector.

  3. Name it MartechDB, paste the address below and click Add. There's no sign-in.

The free plan allows one custom connector. On Team and Enterprise plans, an owner adds the connector first.

Show that your MCP server is verified

If you work at Kealabs, add this badge to your MCP docs or README. It's free, it's the same for every vendor, and it updates from our daily checks: it shows uptime while the server responds, and says so if it stops.

Official MCP server, verified by MartechDB
HTML
Markdown

Something wrong or out of date? Suggest a correction or email us, and we'll check it against the evidence. Every correction we make is listed on Corrections.