Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@KIPRIS Plus MCP Server 삼성전자의 AI 반도체 관련 최신 특허 10건 검색해줘"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
KIPRIS Plus Open API를 MCP(Model Context Protocol) 도구로 제공하는 서버입니다.
Claude Desktop, Cursor, 기타 MCP 호환 클라이언트에 등록해 사용합니다.
도구명 | 설명 |
| KIPRIS 검색식(query) 직접 입력 검색 |
| 필드별 조건 입력 검색 (출원인·발명자·IPC·날짜 등) |
| 키워드 자유 검색 |
| 출원번호로 서지정보 단건 조회 |
| 자연어 → KIPRIS 검색식 변환 |
Related MCP server: Korean Patent MCP
Node.js 18 이상 (nodejs.org 에서 설치)
KIPRIS Plus API 키 (plus.kipris.or.kr 에서 회원가입 후 발급)
# 프로젝트 폴더로 이동
cd kipris-mcp
# 의존성 설치
npm install설정 파일 위치:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
아래 내용을 mcpServers 블록에 추가합니다:
{
"mcpServers": {
"kipris": {
"command": "node",
"args": ["/절대경로/kipris-mcp/src/index.js"],
"env": {
"KIPRIS_API_KEY": "여기에_발급받은_API키_입력"
}
}
}
}
args의 경로를 실제 절대경로로 교체하세요.
예(macOS):"/Users/yourname/kipris-mcp/src/index.js"
예(Windows):"C:\\Users\\yourname\\kipris-mcp\\src\\index.js"
.cursor/mcp.json 또는 Cursor 설정의 MCP 섹션에 동일하게 추가합니다.
stdio 기반 MCP 서버로, 아래 명령으로 직접 실행합니다:
KIPRIS_API_KEY=발급키 node src/index.jsClaude에게 아래와 같이 요청할 수 있습니다:
삼성전자의 배터리 관련 특허를 최신 순으로 30건 검색해줘
LG화학이나 삼성SDI가 2021년 이후 출원한 전고체 배터리 특허를 찾아줘
출원번호 1020200012345의 서지정보를 조회해줘
"홍길동 발명자의 반도체 공정 특허"를 KIPRIS 검색식으로 변환하고 검색해줘연산자 | 기호 | 예시 |
AND |
|
|
OR |
|
|
NOT |
|
|
필드코드 | 의미 | 예시 |
| 발명의 명칭 |
|
| 요약 |
|
| 청구범위 |
|
| 출원인 |
|
| 발명자 |
|
| IPC 분류코드 |
|
| 출원일 범위 |
|
| 등록일 범위 |
|
검색 결과에는 KIPRIS 홈페이지 기본 제공 항목이 그대로 포함됩니다:
필드 | 설명 |
발명의명칭 | 특허/실용신안 발명 명칭 |
출원번호 | 출원 번호 |
출원일 | 출원 일자 |
출원인 | 출원인명 |
발명자 | 발명자명 |
대리인 | 대리인(특허법인)명 |
등록번호 | 등록 번호 |
등록일 | 등록 일자 |
공개번호 | 공개 번호 |
공개일 | 공개 일자 |
공고번호 | 공고 번호 |
공고일 | 공고 일자 |
IPC | IPC 분류코드 |
CPC | CPC 분류코드 |
상태 | 특허 상태 (등록/공개/공고/소멸 등) |
요약 | 발명 요약(초록) |
검색 결과 500건 초과 시 경고 메시지가 반환됩니다. 조건을 구체화해 범위를 한정하세요.
KIPRIS Plus API 무료 계정은 월 1,000건, 초당 50건 미만 호출 제한이 있습니다.
API 키는 환경변수 KIPRIS_API_KEY로만 전달하세요. 코드에 직접 삽입하지 마세요.
KIPRIS Plus 서지정보 상세 조회. 출원번호로 단건 특허의 상세 서지정보를 가져옵니다.
| Name | Required | Description | Default |
|---|---|---|---|
| applicationNumber | Yes | 출원번호. 예: 1020200012345 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves detailed bibliographic information, implying a read-only operation, but doesn't disclose other behavioral traits such as authentication requirements, rate limits, error handling, or response format. For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, consisting of two concise sentences that directly state the tool's purpose and usage. There is no wasted language, and every sentence contributes essential information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (a single-parameter lookup tool), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what the return values include (e.g., fields in the bibliographic information), error conditions, or other contextual details needed for effective use. The description should provide more context to compensate for the absence of structured data.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds minimal meaning beyond the input schema. It mentions that the parameter 'applicationNumber' is used to fetch detailed bibliographic information for a single patent, but the schema already has 100% coverage with a clear description and example. Since schema_description_coverage is high, the baseline is 3, and the description doesn't significantly enhance parameter understanding beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'KIPRIS Plus 서지정보 상세 조회' (KIPRIS Plus bibliographic detail lookup) and specifies it retrieves detailed bibliographic information for a single patent using an application number. It distinguishes from siblings by focusing on detailed lookup rather than search or query-building operations. However, it doesn't explicitly contrast with specific sibling tools like 'kipris_item_search' which might also retrieve patent details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides minimal usage guidance: it indicates the tool is for retrieving detailed bibliographic information by application number. However, it offers no explicit guidance on when to use this tool versus alternatives (e.g., when to use 'kipris_search' for broader searches or 'kipris_item_search' for other item types), no prerequisites, and no exclusions. Usage is implied but not clearly articulated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
자연어 검색 의도를 KIPRIS 검색식(query)으로 변환합니다. 변환 결과를 kipris_search에 전달해 실제 검색을 수행하세요.
| Name | Required | Description | Default |
|---|---|---|---|
| intent | Yes | 자연어 검색 의도. 예: '삼성전자의 배터리 특허 2020년 이후', '홍길동 발명자의 반도체 특허' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It describes the conversion behavior but lacks details on potential limitations, error handling, or output format. For a tool with no annotation coverage, this is a significant gap in behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, consisting of two concise sentences that directly explain the tool's function and usage without any wasted words. Every sentence earns its place by providing essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (simple conversion with one parameter), no annotations, and no output schema, the description is adequate but incomplete. It explains the purpose and basic usage but lacks details on output format or behavioral traits, which are needed for full contextual understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the schema already documents the single parameter 'intent' with examples. The description adds minimal value by restating '자연어 검색 의도' but doesn't provide additional syntax or format details beyond what the schema provides, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: converting natural language search intent into KIPRIS search queries. It specifies the input ('자연어 검색 의도') and output ('KIPRIS 검색식'), though it doesn't explicitly differentiate from all sibling tools like kipris_free_search or kipris_search beyond mentioning the latter as the next step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use this tool: for converting natural language intent into a structured query, and it explicitly states to pass the result to kipris_search for actual searching. However, it doesn't mention when not to use it or alternatives among siblings like kipris_free_search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KIPRIS Plus CPC 코드 검색. CPC 분류코드로 특허/실용신안을 검색합니다. getAdvancedSearch와 별개의 전용 엔드포인트(cpcSearchInfo)를 사용하며, 특허/실용 포함 여부 및 행정처분 상태 필터를 지원합니다.
| Name | Required | Description | Default |
|---|---|---|---|
| cpcNumber | Yes | CPC 분류코드. 예: H01M10/00, B60L50 | |
| patent | No | 특허 포함 여부 (기본 true) | |
| utility | No | 실용신안 포함 여부 (기본 true) | |
| lastvalue | No | 행정처분 필터. 공백=전체, A=공개, C=취하, F=소멸, G=포기, I=무효, J=거절, R=등록 | |
| docsCount | No | 페이지당 건수 (최대 500, 기본 30) | |
| docsStart | No | 시작 페이지 번호 (기본 1) | |
| sortSpec | No | 정렬 기준: AD=출원일, GD=등록일, OPD=공개일, PD=공고일 (기본 AD) | AD |
| descSort | No | 내림차순 정렬 (기본 true = 최신순) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It mentions the tool supports patent/utility inclusion filters and administrative status filters, which adds useful context. However, it doesn't disclose important behavioral traits like rate limits, authentication requirements, pagination behavior, or what the response format looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately concise with two sentences that efficiently convey the tool's purpose and key features. It's front-loaded with the core functionality and follows with supporting details about the endpoint and filters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with 8 parameters, 100% schema coverage, but no annotations or output schema, the description provides adequate context about what the tool does and its endpoint distinction. However, it lacks information about response format, error handling, and other behavioral aspects that would be helpful for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description mentions patent/utility inclusion and administrative status filters, which aligns with parameters but doesn't add significant meaning beyond what the schema provides. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for patents/utility models using CPC classification codes, with specific mention of patent/utility inclusion and administrative status filters. It distinguishes from 'getAdvancedSearch' by mentioning a dedicated endpoint, but doesn't explicitly differentiate from sibling tools like 'kipris_search' or 'kipris_free_search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context about when to use this tool by mentioning it uses a dedicated endpoint separate from 'getAdvancedSearch' and supports specific filters. However, it doesn't explicitly state when NOT to use it or provide alternatives among the sibling tools listed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KIPRIS Plus 자유 검색. 키워드를 입력하면 발명명칭·요약·청구범위 전체에서 검색합니다.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | 검색 키워드. 예: 배터리 전극, 인공지능 이미지 | |
| numOfRows | No | 반환 건수 (최대 500, 기본 50) | |
| pageNo | No | 페이지 번호 (기본 1) | |
| sortSpec | No | AD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the search scope but lacks critical details: whether this is a read-only operation, any rate limits, authentication requirements, or what the output format looks like (since no output schema exists). For a search tool with 4 parameters, this is insufficient behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, consisting of two sentences that directly state the tool's function and scope. There's no wasted text, though it could be slightly more structured (e.g., separating scope from action).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (4 parameters, no annotations, no output schema), the description is incomplete. It lacks behavioral details (e.g., read-only status, output format), usage guidelines relative to siblings, and full parameter context. For a search tool in a suite with multiple similar tools, this leaves significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds minimal parameter semantics beyond the schema. It mentions '키워드를 입력하면' (if you input a keyword), which aligns with the 'keyword' parameter, but doesn't explain the other parameters (numOfRows, pageNo, sortSpec). With 75% schema description coverage (3 of 4 parameters have descriptions), the baseline is 3, as the schema does most of the work, but the description doesn't compensate for the remaining gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'KIPRIS Plus 자유 검색' (free search) that searches across '발명명칭·요약·청구범위 전체' (invention name, abstract, and claims). It specifies the verb (search) and resource (patent documents), but doesn't explicitly differentiate from sibling tools like 'kipris_search' or 'kipris_item_search', which likely have different search scopes or methods.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its siblings (e.g., kipris_search, kipris_item_search). It mentions the search scope (invention name, abstract, claims) but doesn't specify alternatives or exclusions, leaving the agent to guess based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KIPRIS Plus 항목별 검색. 발명명칭·출원인·발명자·IPC·날짜 등 각 필드를 개별 입력해 검색합니다. getAdvancedSearch API를 사용하며 공식 파라미터명(inventionTitle, applicant, inventors 등)으로 전송합니다.
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | 발명의 명칭 (inventionTitle). 예: 배터리 | |
| abstract | No | 초록/요약 키워드 (astrtCont) | |
| claims | No | 청구범위 키워드 (claimScope) | |
| applicant | No | 출원인명 또는 특허고객번호 (applicant). 예: 삼성전자 | |
| inventor | No | 발명자명 또는 특허고객번호 (inventors). 예: 홍길동 | |
| ipc | No | IPC 분류코드 (ipcNumber). 예: H01M, H01L21 | |
| applicationDateFrom | No | 출원일 시작 (YYYYMMDD) | |
| applicationDateTo | No | 출원일 종료 (YYYYMMDD) | |
| registerDateFrom | No | 등록일 시작 (YYYYMMDD) | |
| registerDateTo | No | 등록일 종료 (YYYYMMDD) | |
| openDateFrom | No | 공개일 시작 (YYYYMMDD) | |
| openDateTo | No | 공개일 종료 (YYYYMMDD) | |
| numOfRows | No | 반환 건수 (최대 500, 기본 50) | |
| pageNo | No | 페이지 번호 (기본 1) | |
| sortSpec | No | 정렬 기준 (기본 AD=출원일) | AD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the API used and that parameters are sent using '공식 파라미터명' (official parameter names), but doesn't describe what the tool returns, pagination behavior, rate limits, authentication requirements, or error handling. For a search tool with 15 parameters, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately concise with two sentences that convey the core functionality and technical implementation. It's front-loaded with the main purpose and efficiently mentions the API usage without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex search tool with 15 parameters and no output schema, the description is incomplete. It doesn't explain what results are returned, their format, or how to interpret them. With no annotations and no output schema, the agent lacks crucial information about the tool's behavior and output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 15 parameters thoroughly with examples and defaults. The description adds minimal value by mentioning that parameters correspond to '공식 파라미터명' (official parameter names) like 'inventionTitle, applicant, inventors', but doesn't provide additional semantic context beyond what's in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs 'KIPRIS Plus 항목별 검색' (item-by-item search) and specifies it searches by individual fields like invention title, applicant, inventor, IPC, and dates. It mentions using the 'getAdvancedSearch API' which provides technical context. However, it doesn't explicitly differentiate from sibling tools like 'kipris_free_search' or 'kipris_search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'kipris_free_search' or 'kipris_search'. It mentions the API used ('getAdvancedSearch API') but doesn't explain what makes this tool distinct from its siblings or when it's the appropriate choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KIPRIS Plus 키워드 검색. 자유 키워드로 특허/실용신안 전문(발명명칭·요약·청구범위)을 검색합니다. 특정 필드(출원인, 발명자, IPC 등)로 좁혀 검색하려면 kipris_item_search를 사용하세요.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 검색 키워드. 예: 배터리 전극, 인공지능 이미지 인식 | |
| numOfRows | No | 반환 건수 (최대 500, 기본 50) | |
| pageNo | No | 페이지 번호 (기본 1) | |
| sortSpec | No | 정렬 기준: AD=출원일, GD=등록일, OPD=공개일, PD=공고일 (기본 AD) | AD |
| descSort | No | 내림차순 정렬 (기본 true = 최신순) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the scope of the search (full text across multiple fields) and mentions the sibling alternative, but doesn't describe what the tool returns, any rate limits, authentication requirements, or potential side effects. The description adds some context but lacks comprehensive behavioral information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (two sentences) and front-loaded with the core purpose. Every sentence earns its place: the first states what the tool does, the second provides clear usage guidance. There's zero wasted text or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters with 100% schema coverage but no annotations and no output schema, the description provides adequate purpose and usage guidance but lacks information about what the tool returns. For a search tool with no output schema, the description should ideally mention the type of results returned (e.g., patent documents, metadata). The current description is complete for basic usage but has gaps in behavioral context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already fully documents all 5 parameters. The description doesn't add any parameter-specific information beyond what's in the schema. It mentions '자유 키워드' (free keywords) which aligns with the query parameter, but provides no additional syntax, format, or usage details. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('키워드 검색' - keyword search) and resource ('특허/실용신안 전문' - patent/utility model full text), distinguishing it from the sibling tool kipris_item_search for field-specific searches. It explicitly mentions searching across multiple text fields (invention name, summary, claims).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool ('자유 키워드로' - with free keywords) versus when to use the alternative ('특정 필드로 좁혀 검색하려면 kipris_item_search를 사용하세요' - use kipris_item_search for narrowing by specific fields). This clearly distinguishes it from the sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0kipris_bibliographykipris_build_querykipris_cpc_searchkipris_free_searchkipris_item_searchkipris_searchScored across 6 tools
Each tool has a clearly distinct purpose: kipris_bibliography retrieves detailed bibliographic information for a single patent, kipris_build_query converts natural language to a search query, kipris_cpc_search searches by CPC code, kipris_free_search performs keyword searches across all fields, kipris_item_search allows field-specific searches, and kipris_search handles keyword searches in patent text. There is no overlap or ambiguity between these functions.
All tool names follow a consistent pattern: they start with 'kipris_' followed by a descriptive term (e.g., bibliography, build_query, cpc_search). This uniform prefix and snake_case structure make the tools easily identifiable and predictable.
With 6 tools, this server is well-scoped for patent search and retrieval. It covers key operations like detailed lookups, query building, and various search methods (CPC, free, item-specific), which is appropriate for the domain without being overwhelming or insufficient.
The tool set provides comprehensive coverage for patent search and retrieval, including query building, multiple search types, and detailed information access. A minor gap is the lack of explicit update or delete operations, but this is reasonable given the server's focus on querying a static patent database, and agents can work effectively with the provided tools.
Korean patents by meaning, not keywords: describe an invention in plain words or by drawing.
Global patent search, briefs, similarity, citations and landscape stats. Strong China coverage.
AI-powered patent intelligence for search & analysis
Patent search, USPTO data, patent landscape & pgvector prior-art search for agents.
