Nexscope

Design Similarity Search

Find similar design-registration candidates from a product image with region, Locarno and legal-status filters. Review evidence through REST API or MCP.

CostRecent 11 credits / call
Try online
POST Β· https://api.nexscope.ai/ai/designSimilaritySearchMCP Β· nexscope_design_similarity_search

What this API does

Find similar design-registration candidates using exactly one imageUrl or imageBase64. Base64 accepts 16–20971520 encoded characters. Preserve source order, coverage and warnings. Use image_url only when actually returned; image_available alone does not provide a URL. Results support review and do not establish infringement or freedom to operate.

Design Similarity Search API use cases

Search from an image URL

Supply the actual user-selected imageUrl to find similar design registrations and omit imageBase64. Apply only the requested region, Locarno and legal-status filters.

Search from local image bytes

Encode the local image as pure Base64 and supply imageBase64 without imageUrl. Keep the encoded text within the documented 16–20971520 character limit.

Review registration candidates

Retain returned candidate IDs, source order, coverage and warnings. Use a returned image_url unchanged. If the user requests details, reuse actual design_registration_id values in the separate registration-details operation.

Design Similarity Search API FAQ

What does the Design Similarity Search API return?

Find similar design-registration candidates from a product image with region, Locarno and legal-status filters. Review evidence through REST API or MCP. The documented output includes candidates.applicant_addresses.address, candidates.applicant_addresses.name, candidates.application_date, candidates.application_number, candidates.design_registration_id, candidates.designer_names, candidates.estimated_expiration_date, candidates.expiration_date_basis. It corresponds to the supplied imageUrl, imageBase64, title, topK, regions. Optional fields can be absent; a missing value should not be interpreted as a measured zero. Example values illustrate the response shape, rather than live account results.

How many credits does the Design Similarity Search API cost?

The current documented cost is Recent 11 credits / call. This is the same cost shown at the top of this page. If a range or estimate is displayed, the final charge depends on the request. Review your available credits and the pricing page before calling the API, and check API usage records for the actual charge.

How do I call the Design Similarity Search API from my app or an MCP client?

Send a POST request to https://api.nexscope.ai/ai/designSimilaritySearch with your API key as a Bearer token and the JSON inputs shown in API integration. In a compatible MCP client such as Claude or Cursor, connect Nexscope and call nexscope_design_similarity_search. Use the MCP arguments shown in the MCP guide, or switch Online test to MCP to review its request before adding it to your app.

View plans and creditsConnect this API with MCP

Try this API
Endpoint
https://api.nexscope.ai/ai/designSimilaritySearch
MCP method
nexscope_design_similarity_search

Step 1 of 3 Β· Authenticate

Authentication

All run endpoints require a user API key. Send it as a bearer token in the Authorization header.

Authorization: Bearer nk-xxxxxxxxxxxxxxxxx
Missing or invalid API keys return an authentication error. Manage keys from .

Step 2 of 3 Β· Send a request

POSThttps://api.nexscope.ai/ai/designSimilaritySearch

Run an API

Send a JSON request body using the parameters described below.

Example request

Replace YOUR_API_KEY, then run this command in your terminal.

curl -X POST 'https://api.nexscope.ai/ai/designSimilaritySearch' \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "imageUrl": "https://example.com/product.png",
  "title": "Bottle",
  "topK": 20
}'

Code example

{
  "imageUrl": "https://example.com/product.png",
  "title": "Bottle",
  "topK": 20
}

Step 3 of 3 Β· Inspect the result

Check the response

Read code for the request status and data for the result. Open the parameter and response reference for the full field definitions.

HTTP status codes

CodeDescription
200Default HTTP response for both success and many business errors. Only outer JSON code 0 indicates success or asynchronous acceptance; inspect data for the result.
429Execution admission rate limit; honor Retry-After when present.
503Execution admission is temporarily unavailable; honor Retry-After when present.
Opt-inX-Nexscope-Http-Status: semantic maps controller-handled business errors to HTTP status on run and task routes. Pre-authentication failures, such as a missing or invalid API key (code 11209, including an incomplete or corrupted copy) or an expired website login session (code 12001), may still return HTTP 200 before this mapping. Always check the outer JSON code; malformed requests and infrastructure failures may also return non-200 HTTP responses.
All categories/ Design Registration Research

Step 1 of 2 Β· Connect your MCP client

MCP

V2 recommended

Connect remote agents through the standard MCP 2025-11-25 Streamable HTTP endpoint. Use OAuth 2.1 Authorization Code with PKCE, or an API key for compatibility.

POST https://api.nexscope.ai/mcp
MCP-Protocol-Version: 2025-11-25
Content-Type: application/json
Authentication

OAuth clients request the mcp:tools scope. The endpoint's 401 response advertises protected-resource metadata for authorization discovery.

Step 2 of 2 Β· Call the tool

Call a tool

{
  "jsonrpc": "2.0",
  "id": "tool-call-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_design_similarity_search",
    "arguments": {
      "imageUrl": "https://example.com/product.png",
      "title": "Bottle",
      "topK": 20
    }
  }
}

Legacy MCP v1

Existing API-key clients can continue using the compatibility endpoint. New integrations should use MCP v2.

GET / POST /mcp/legacy

What can you do with this API?

Data explained and practical use cases

AI Guide

Question

What results can Design Similarity Search provide, and how might I use them?

AI answer

Submit one image URL or Base64 image to find visually similar design-registration candidates. The result is a review list with similarity scores and available registration details, not a legal determination.

Data categoryDocumented fieldsWhat the values mean
Candidate identitydesign_registration_id, primary_identifier, title_enIdentifies a returned registration candidate and its available English title.
Similarity and review signalsimilarity, risk_levelA reported similarity score and risk label to help prioritize review; neither establishes infringement.
Jurisdiction and classificationjurisdiction_iso2, registration_jurisdiction_code, protected_jurisdictions, locarno_classesReported jurisdictions and design classifications for the candidate.
Ownership and statusholder_names, designer_names, simple_legal_statusAvailable holder, designer, and simplified status information; values may be null.
Dates and imagesapplication_date, registration_date, image_url, imagesAvailable dates and image links. Use image_url or images only when links are actually returned.
Result sizetotal, candidatesThe reported candidate count and candidate list.
  • Upload a product image and review the highest-scoring design candidates alongside their registration identifiers.
    • Prompt example: β€œI am researching products for an online store. I can provide a product image URL or Base64 value. Could you review the highest-scoring design candidates alongside their registration identifiers? Show the relevant returned evidence and tell me what input you need from me.”
  • Limit a search to selected regions or Locarno classes to focus a design research queue.
    • Prompt example: β€œI am researching products for an online store. Could you limit a search to selected regions or Locarno classes to focus a design research queue? Show matching records and source links where the API provides them; ask me for any required identifier or filter.”
  • Open returned candidate image links to compare specific visual features with the submitted image.
    • Prompt example: β€œI am researching products for an online store. Could you open returned candidate image links to compare specific visual features with the submitted image? Show the returned values behind the comparison, and mark missing data.”
  • Use holder, status, and jurisdiction fields to decide which candidates need deeper registration review.
    • Prompt example: β€œI am researching products for an online store. Could you use holder, status, and jurisdiction fields to decide which candidates need deeper registration review? Show the relevant returned evidence and tell me what input you need from me.”

A match, score, or risk label does not establish infringement or freedom to operate. Coverage and missing values should be considered when interpreting the results.

Related APIs