SOTA2 — AI Solution Rankings
Compare published AI solution rankings, company facts and research benchmarks with sources.
사용해야 할까요
품질 및 안전성
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"sota2": {
"url": "https://www.sota2.com/mcp"
}
}
}원격 엔드포인트
https://www.sota2.com/mcpstreamable-http할 수 있는 일
도구 목록
도구 (11)
🟢search_companies(query, limit)
Resolves a named AI company to stable IDs, names and descriptions. Revenue-only records can have null catalog slug and profile URL; their returned ID remains usable for company lookup. Matches depend on spelling and available aliases; no matches do not prove a language is unsupported or a company does not exist. Ambiguous names can have multiple matches. This searches company identities rather than category leaderboards. Generic verification queries return no company rows and clarification_required with identities/KYC, document authenticity and factual-claim meanings.
입력 스키마
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 2,
"maxLength": 120
},
"limit": {
"default": 20,
"description": "Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.",
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"required": [
"query"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢get_company(company, dimensions, limit, offset)
Returns public data for an exact company ID or slug. Company and product soc2Disclosure states are separately reported_claims or unknown_not_disclosed, with original vendor claim statuses rather than independent certification. Available dimensions: profile, products, compliance, customers, deployment, funding, solution ranking appearances and revenue. Defaults to all dimensions. Missing catalog records may still have ranking or revenue data. Each collection has independent pagination using the same limit/offset.
입력 스키마
{
"type": "object",
"properties": {
"company": {
"type": "string",
"minLength": 1,
"maxLength": 160,
"description": "Exact returned company ID or slug."
},
"dimensions": {
"default": [
"profile",
"products",
"compliance",
"customers",
"deployment",
"funding",
"rankings",
"revenue"
],
"minItems": 1,
"maxItems": 8,
"type": "array",
"items": {
"type": "string",
"enum": [
"profile",
"products",
"compliance",
"customers",
"deployment",
"funding",
"rankings",
"revenue"
]
}
},
"limit": {
"default": 20,
"description": "Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"default": 0,
"description": "Row offset. Use nextOffset from the previous response.",
"type": "integer",
"minimum": 0,
"maximum": 100000
}
},
"required": [
"company"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢list_industries(query, limit, offset)
Lists supported industries with canonical IDs/slugs, names, descriptions and aliases. Includes cross-industry, consumer and agent audiences when available. An optional query filters this directory; without it the directory is browsable with pagination.
입력 스키마
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 120
},
"limit": {
"default": 20,
"description": "Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"default": 0,
"description": "Row offset. Use nextOffset from the previous response.",
"type": "integer",
"minimum": 0,
"maximum": 100000
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢list_tasks(industry, query, limit, offset)
Lists AI solution task IDs, slugs, descriptions and company coverage, optionally within an industry. An optional query filters the directory. Ambiguous 'AI verification platform', 'verification' and 'verify' queries include clarification_required with identities/KYC, document authenticity and factual-claim choices; these have no selected meaning. Company coverage overlaps across tasks, so task counts are not additive distinct-company totals.
입력 스키마
{
"type": "object",
"properties": {
"industry": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"query": {
"type": "string",
"minLength": 1,
"maxLength": 120
},
"limit": {
"default": 20,
"description": "Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"default": 0,
"description": "Row offset. Use nextOffset from the previous response.",
"type": "integer",
"minimum": 0,
"maximum": 100000
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢get_solution_rankings(industry, task, limit, offset)
Returns published AI solution rankings for a specified industry/task. Industry only returns its task directory and cross-industry links; industry + task selects that exact scope; task only selects cross-industry. Missing entities/combinations return normal not_found results with discovery guidance, never another scope. Ambiguous categories return needs_selection or clarification_required. Positions/scores apply within the selected scope; cross-scope quality differences are not established. Top N corresponds to limit N rows. Unreviewed positions/scores are null.
입력 스키마
{
"type": "object",
"properties": {
"industry": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"task": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"limit": {
"default": 20,
"description": "Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"default": 0,
"description": "Row offset. Use nextOffset from the previous response.",
"type": "integer",
"minimum": 0,
"maximum": 100000
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢list_company_leaderboards
List supported AI company leaderboards by annual revenue, country/region and category. Returns IDs, scope, descriptions and source URLs. Country lists rank companies within a geography; they do not rank countries.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢get_company_leaderboard(leaderboard, limit, offset)
Returns a published AI company leaderboard by its exact ID, e.g. ai-global, ai-usa or ai-china. Includes ranks and ties, revenue in USD, reporting basis, period, confidence and original sources. Revenue, ARR, run-rate, forecasts and estimates have distinct basis labels.
입력 스키마
{
"type": "object",
"properties": {
"leaderboard": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"limit": {
"default": 20,
"description": "Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"default": 0,
"description": "Row offset. Use nextOffset from the previous response.",
"type": "integer",
"minimum": 0,
"maximum": 100000
}
},
"required": [
"leaderboard"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢list_research_domains(query)
Lists AI research fields with canonical slugs and descriptions, such as NLP, computer vision, agents/tool use and RAG. These are research domains, separate from commercial company industries. An optional query filters the domain directory.
입력 스키마
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 120
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢search_research(resource, query, page, domain, task, ...)
Searches research benchmarks, datasets, tasks or papers using keywords, benchmark/dataset names, paper titles, authors or arXiv identifiers. Returns 20 results per API page. Versions, test splits and Full/Hard variants can be separate benchmarks. Search summaries are discovery data, not validated performance ranks. Paper search requires query and has no count/date sort. Dataset/task/benchmark count sorts order discovery results, not cross-benchmark performance.
입력 스키마
{
"type": "object",
"properties": {
"resource": {
"default": "benchmarks",
"type": "string",
"enum": [
"benchmarks",
"datasets",
"papers",
"tasks"
]
},
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200
},
"page": {
"default": 1,
"type": "integer",
"minimum": 1,
"maximum": 1000
},
"domain": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"task": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"dataset": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"sort": {
"type": "string",
"enum": [
"last_update",
"papers",
"results",
"benchmarks"
]
}
},
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢get_research_entity(type, identifier, page)
Returns one exact research entity. Dataset identifiers are dataset-FAMILY slugs (e.g. omnidocbench), not version slugs (e.g. omnidocbench-v1-5); family details include benchmarks across versions. Task/domain identifiers are canonical slugs; paper identifiers are 24-character paper IDs rather than arXiv IDs. Task/dataset details include benchmark links; domain details include research tasks. Paper details include abstract, authors, original/PDF/code links and related benchmarks when available. Missing entities return normal not_found results; API failures remain tool errors.
입력 스키마
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"task",
"dataset",
"paper",
"domain"
]
},
"identifier": {
"type": "string",
"minLength": 1,
"maxLength": 500,
"description": "Dataset: canonical dataset-FAMILY slug, not a version slug; task/domain: canonical slug; paper: canonical 24-character paper ID."
},
"page": {
"default": 1,
"type": "integer",
"minimum": 1,
"maximum": 1000
}
},
"required": [
"type",
"identifier"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢get_research_benchmark(benchmark, metric, method, limit, offset)
Returns individual reported result rows for one exact benchmark version/split and metric. Top N corresponds to limit N rows, each identified by resultId with exact method, configuration and global position, including ties. Rows are not deduplicated or grouped into method families. The optional method substring filter applies to the complete ranked benchmark before pagination, preserving global positions. results.nextCall contains exact continuation arguments. Includes metric direction, completeness checks, invalid-percentage warnings and separate reporting/origin papers.
입력 스키마
{
"type": "object",
"properties": {
"benchmark": {
"type": "string",
"minLength": 1,
"maxLength": 500,
"description": "Canonical benchmark slug from discovery, e.g. document-parsing-on-omnidocbench-v1-5. A display name such as OmniDocBench v1.5 returns discovery choices instead of result rows; no version or split is silently selected."
},
"metric": {
"type": "string",
"minLength": 1,
"maxLength": 500,
"description": "Exact metric name for this benchmark. A different metric defines a new result selection starting at offset 0."
},
"method": {
"type": "string",
"minLength": 1,
"maxLength": 120,
"description": "Optional method name substring, e.g. PaddleOCR-VL for PaddleOCR-VL-related results. Case-insensitive filtering over the complete ranked benchmark before pagination; part of the selection on every filtered page. Positions remain global."
},
"limit": {
"default": 20,
"description": "Requested number of individual result rows (1–50): top 2 corresponds to limit 2. Also the page size for continuation requests.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"default": 0,
"description": "Row offset. Use nextOffset from the previous response.",
"type": "integer",
"minimum": 0,
"maximum": 100000
}
},
"required": [
"benchmark"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"data": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"data"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}커뮤니티
증거