Nexscope Ecommerce Data MCP

Patent Intelligence ZY: patent Image Search API

nexscope_data_zy_patent_image_search

Patent Intelligence ZY: patent Image Search API.

Input Schema

Name	Required	Description	Default
`loc`	No	LOC classification, multiple classification numbers can be connected using `AND`/`OR`/`NOT`.
`url`	Yes	Image URL, maximum 1,000 characters.
`lang`	No	Title language: `original` (original text), `cn` (Chinese translation), `en` (English translation).	original
`field`	No	Sorting fields: `SCORE` (relevance), `APD` (application date), `PBD` (publication date), `ISD` (authorization date).	SCORE
`limit`	No	Returns the number of patents, 1–100.
`model`	Yes	Appearance patents: `1` (intelligent Lenovo, recommended), `2` (search this picture); utility models: `3` (matching shape), `4` (matching shape/pattern/color, recommended).
`order`	No	Valid when `field` is a date field: `desc` or `asc`.	desc
`offset`	No	Offset, 0–1000.
`country`	No	The country/organization/region code of the patent acceptance office. Multiple ones are separated by English commas; if not passed, it means all the acceptance offices.
`isHttps`	No	Image domain name protocol: `1` returns HTTPS, `0` returns HTTP.
`stemming`	No	Whether to turn on truncation: `1` is on, `0` is off.
`assignees`	No	Applicant (patent rights), maximum 1,000 characters.
`mainField`	No	Main patent fields, including title, abstract, claims, specification, publication number, application number, applicant, inventor, and IPC/UPC/LOC classification number, maximum 1,000 characters.
`preFilter`	No	Whether to enable prefix country/LOC filtering: `1` is on, `0` is off.
`patentType`	Yes	Patent type: `D` (appearance patent) or `U` (utility model patent); the utility model skill uses `U` permanently.
`legalStatus`	No	Detailed legal status codes, multiple separated by English commas: `1` public, `2` substantive review, `3` authorized, `8` avoid repeated authorization, `11` withdrawn, `12` withdrawn-unspecified type, `17` Withdrawal - deemed withdrawal, `18` withdrawal - active withdrawal, `13` rejection, `14` all withdrawal, `15` expiration of term, `16` unpaid annual fee, `21` rights restoration, `22` rights termination, `23` Partially invalid, `24` application terminated, `30` abandoned, `19` abandoned - deemed abandoned, `20` abandoned - voluntary abandoned, `25` abandoned - unspecified type, `222` PCT did not enter the designated country - within the designated period, `223` PCT Entering the designated country - within the designation period, `224` PCT entering the designated country - the designation period expires, `225` PCT not entering the designated country - the designation period expires.
`returnImgId`	No	Whether to return `imgId`.
`applyEndTime`	No	Application deadline, format `yyyyMMdd`.
`publicEndTime`	No	Public deadline, format `yyyyMMdd`.
`applyStartTime`	No	Application start date, format `yyyyMMdd`.
`scoreExpansion`	No	Whether to perform score expansion.
`publicStartTime`	No	Publication start date, format `yyyyMMdd`.
`simpleLegalStatus`	No	Simple legal status: `0` expired, `1` valid, `2` under review, `220` PCT designated expiration, `221` PCT designated period, `999` unconfirmed.
`includeMachineTranslation`	No	Whether the search includes machine translation data.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 24, 2026

TDQS

D1.9/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses no behavior at all beyond what the title already implies — no return shape, no pagination/limit behavior, no note on why a search tool carries readOnlyHint=false, no cost or rate-limit context. With annotations present but terse, the description contributes nothing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but short by omission rather than economy — a single redundant sentence that duplicates the title. Nothing is front-loaded because nothing of substance is stated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A 24-parameter search tool with no output schema needs the description to set expectations about results, ranking, and pagination. None of that is present, so the definition is inadequate for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and all 24 parameters (including the tricky model/patentType pairing) are documented in the schema. Per the high-coverage baseline this lands at 3, though the description itself adds zero parameter meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Patent Intelligence ZY: patent Image Search API" only restates the name and title. It does gesture at the resource (patent images), but there is no specific verb or scope, and it never distinguishes this from nexscope_zhihuiya_patent_image_search or nexscope_data_rg_detection_patent_design.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No statement of when to use this tool, when not to, or which sibling handles adjacent cases. An agent must infer usage purely from the name, with no exclusions or prerequisites given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Nexscope Ecommerce Data MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?