IP Risk Detection RG
Design Patent Risk Check MCP
Detect design-patent risks by comparing a product image with patent records across more than 25 jurisdictions. Call it via REST API or MCP.
Design Patent Risk Check AI Prompts & Use Cases
After connecting this MCP tool to your AI assistant, you can ask the questions below. Replace bracketed placeholders with your own inputs and use the supported values in Arguments.
New to Nexscope MCP? Follow the connection guide, then use the prompts below. The Integration and Parameters & Response tabs contain the connection steps, call example, and technical reference.
1. Search Designs From Product Photograph
Prompt: Search for design-patent candidates using [product image] in product photograph mode. Return up to [number no greater than 100] candidates and distinguish similarity signals from legal conclusions.
2. Search Designs From Line Drawing
Prompt: Search for design-patent candidates using [product image] in line drawing mode. Return up to [number no greater than 100] candidates and distinguish similarity signals from legal conclusions.
3. Search Designs From Combined Visual Evidence
Prompt: Search for design-patent candidates using [product image] in combined visual evidence mode. Return up to [number no greater than 100] candidates and distinguish similarity signals from legal conclusions.
4. Add Product Context
Prompt: Search for design-patent candidates using [product image] in product photograph mode. Return up to [number no greater than 100] candidates and distinguish similarity signals from legal conclusions. Use [product title] and [product description] to guide the image search. Translate from [source language] where necessary; leave translation off for English context.
5. Narrow The Patent Search
Prompt: Search for design-patent candidates using [product image] in product photograph mode. Return up to [number no greater than 100] candidates and distinguish similarity signals from legal conclusions. Restrict the search to [supported sale regions], [Locarno classes] and [active, inactive or all patent statuses].
6. Include Radar Analysis
Prompt: Search for design-patent candidates using [product image] in product photograph mode. Return up to [number no greater than 100] candidates and distinguish similarity signals from legal conclusions. Choose whether to add radar analysis to the candidate review. Keep its risk indicators separate from a legal determination.
What You Need to Provide
Use returned matches and legal-status fields as research leads. They do not establish ownership, infringement, validity or freedom to operate. Dates and jurisdiction coverage must remain explicit.
Step 1 · Connect
Connect Your AI Assistant
Connect a compatible MCP client to Nexscope, then select this tool from your assistant. Use the connection settings in your client to complete authentication.
POST https://api.nexscope.ai/mcp
MCP-Protocol-Version: 2025-11-25
Content-Type: application/jsonAuthentication
Use OAuth 2.1 Authorization Code with PKCE and the mcp:tools scope. API keys remain supported as a compatibility option.
Authorization: Bearer nk-xxxxxxxxxxxxxxxxxUsing an API key? Get your key from API Access and include it in the Authorization header shown above.
Call this MCP tool
nexscope_ruiguan_detection_patent_designhttps://api.nexscope.ai/mcptools/callInitialize an MCP 2025-11-25 Streamable HTTP session at https://api.nexscope.ai/mcp, then use tools/call.
{
"jsonrpc": "2.0",
"id": "ruiguan-detection-patent-design-1",
"method": "tools/call",
"params": {
"name": "nexscope_ruiguan_detection_patent_design",
"arguments": {
"enableRadar": false,
"imageUrl": "https://m.media-amazon.com/images/I/719mRAn2VrL._AC_SL1500_.jpg",
"patentStatus": "1,0",
"productDescription": "A protective smartphone case with a magnetic ring stand and shockproof corners.",
"productTitle": "Magnetic phone case",
"queryMode": "physical",
"regions": "US",
"topNumber": 10
}
}
}MCP 2025-11-25 · Streamable HTTPProgress is delivered on the original POST SSE response. GET SSE carries notifications; reconnecting must query existing asynchronous work rather than submit again.
Arguments
| Name | Type | Required | Description |
|---|---|---|---|
imageUrl | string | required | Product image URL used for comparison with the patent database (maximum 1,000 characters) Example: https://m.media-amazon.com/images/I/719mRAn2VrL._AC_SL1500_.jpg |
queryMode | string | required | Search mode: physical for product-photo search, line for line-drawing search, or hybrid for combined search. Maximum 1,000 characters Example: physical |
topNumber | integer | required | Number of patents to return (maximum 100) Example: 10 |
regions | string | optional | Country or region codes where the product is sold, separated by commas, for example US,EU,CN. Maximum 1,000 characters Available options
Example: US |
productTitle | string | optional | Product title used to provide additional search context (maximum 1,000 characters) Example: Magnetic phone case |
productDescription | string | optional | Product description used to provide additional search context (maximum 1,000 characters) Example: A protective smartphone case with a magnetic ring stand and shockproof corners. |
patentStatus | string | optional | Patent-validity filter: 1 for active patents, 0 for inactive patents, or 1,0 for all patents. Maximum 1,000 characters Example: 1,0 |
enableRadar | boolean | optional | Whether to enable AI radar analysis for potential infringement Example: false |
topLoc | string | optional | Top-level LOC classes to search, for example 06,07. Pattern: ^(0[1-9]\ |
sourceLanguage | string | optional | Source-language code used to translate content into English, for example zh-CN. Leave empty when the text is already English. Maximum 1,000 characters |
Response fields
Treat structuredContent as the programmatic API response payload.
| Name | Type | Required | Description |
|---|---|---|---|
total | integer | optional | Total number of patent records returned |
data | array | optional | Patent list (see patent objects below for details) |
columns | array | optional | Rendered column definitions |
costToken | integer | optional | Consume token |
type | string | optional | Rendering style |
applicationNumber | string | optional | Patent application number |
publicationNumber | string | optional | Patent publication number |
patentProd | string | optional | Patent title (English) |
patentProdCn | string | optional | Patent title (Chinese) |
similarity | string | optional | Similarity between patent and product pictures (0-1) |
patentImageUrl | string | optional | The URL of the patent drawing that is most similar to the product image |
images | array | optional | Patent picture list |
abstracts | string | optional | Patent abstract |
specification | string | optional | patent specification |
inventors | array | optional | List of inventors |
applicants | array | optional | Applicant list |
applicantAddresses | array | optional | Applicant address |
troCase | boolean | optional | Do you have a history of TRO rights protection? |
troHolder | boolean | optional | Is it the patent of the TRO right holder? |
radarResult | object | optional | AI radar analysis results |
radarResult.same | boolean | optional | Is it suspected of infringement? |
radarResult.exp | string | optional | Expected Description (Radar Determination Instructions) |
patentLoc | string | optional | LOC classification of the patent, multiple separated by commas |
locOneInfo | string | optional | LOC Level 1 Details |
locTwoInfo | string | optional | LOC Level 2 Details |
patentValidity | string | optional | patent validity |
applicationDate | string | optional | Patent application date |
publicationDate | string | optional | Patent disclosure date |
grantDate | string | optional | Patent grant date |
estimatedDueDate | string | optional | Estimated maturity date |
registrationOfficeCode | string | optional | Patent Registration and Reception Office |
patentFamily | array | optional | List of patent families |
globalPatentId | string | optional | Global Patent ID |
globalImageId | string | optional | ID of the patent image |
isSketchText | string | optional | Is it a line drawing? |
Format Illustration
Illustrative example with fictional data, not a live tool call.
Illustrative Question
Search for design-patent candidates using [product image] in product photograph mode. Return up to [number no greater than 100] candidates and distinguish similarity signals from legal conclusions.
Illustrative Response Explanation
The illustrative response contains no returned design-patent candidates for this request. An empty result describes this example only; it does not establish complete database coverage or clearance for the product.
About this sample: Illustrative format example with fictional values, not a live tool call. Replace example inputs with your own permitted assets or public identifiers.
Published sample data is not available for this page. A format illustration or workflow guide is not a substitute for a published result.
View the MCP Request & Response Format
Examples
Illustrative example with fictional data, not a live tool call.
The JSON-RPC envelope below illustrates how the shown arguments and payload fit into MCP. It is not captured network traffic or proof of a successful call. Workflow-only examples do not include a result.
MCP Request
{
"jsonrpc": "2.0",
"id": "ruiguan-detection-patent-design-example",
"method": "tools/call",
"params": {
"name": "nexscope_ruiguan_detection_patent_design",
"arguments": {
"enableRadar": false,
"imageUrl": "https://m.media-amazon.com/images/I/719mRAn2VrL._AC_SL1500_.jpg",
"patentStatus": "1,0",
"productDescription": "A protective smartphone case with a magnetic ring stand and shockproof corners.",
"productTitle": "Magnetic phone case",
"queryMode": "physical",
"regions": "US",
"topNumber": 10
}
}
}MCP Response Format
{
"jsonrpc": "2.0",
"id": "ruiguan-detection-patent-design-example",
"result": {
"content": [
{
"type": "text",
"text": "{\"code\":0,\"msg\":null,\"data\":{\"total\":0,\"data\":[]}}"
}
],
"structuredContent": {
"code": 0,
"msg": null,
"data": {
"total": 0,
"data": []
}
},
"isError": false
}
}