このMCPでできること
Classifies, tags, counts, and reviews batches of text using user-defined labels and confidence scores.
機能
ツール
5
ツール
classify_dimensions
Classify several dimensions per text
Classify each text by several named dimensions, such as team, urgency and kind, in one request. Returns a label, confidence, scores and model for each field. At most 1,000 item × dimension decisions; every field counts toward the quota. Use per-dimension instructions to define ambiguous categories.
読み取り専用
外部アクセスあり
入力スキーマ
{'type': 'object', 'oneOf': [{'not': {'required': ['url']}, 'required': ['items']}, {'not': {'required': ['items']}, 'required': ['url']}], 'required': ['dimensions'], 'properties': {'url': {'type': 'string', 'pattern': '^https?://', 'maxLength': 8192, 'description': 'Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.'}, 'tier': {'enum': ['fast', 'smart'], 'type': 'string', 'description': 'fast (default) or smart, which re-asks answers under 0.7 confidence of a reasoning model (slower, single-label only). Independent of the Laya processing lane.'}, 'items': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 1000, 'minItems': 1, 'description': '1 to 1,000 texts to classify. Results come back in the same order.'}, 'model': {'enum': ['jev', 'laya', 'kev', 'chunklaya'], 'type': 'string'}, 'include': {'type': 'array', 'items': {'enum': ['markdown', 'html'], 'type': 'string'}, 'description': 'With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.'}, 'dimensions': {'type': 'object', 'description': 'Named dimensions. Each is a label array or {labels, instructions}. At most 1,000 item × dimension decisions; definitions at most 16,000 characters combined.', 'maxProperties': 20, 'minProperties': 1, 'propertyNames': {'pattern': '\\S', 'maxLength': 64, 'minLength': 1}, 'additionalProperties': {'oneOf': [{'type': 'array', 'items': {'type': 'string', 'pattern': '\\S', 'maxLength': 200, 'minLength': 1}, 'maxItems': 100, 'minItems': 2, 'uniqueItems': True}, {'type': 'object', 'required': ['labels'], 'properties': {'labels': {'type': 'array', 'items': {'type': 'string', 'pattern': '\\S', 'maxLength': 200, 'minLength': 1}, 'maxItems': 100, 'minItems': 2, 'uniqueItems': True}, 'instructions': {'type': 'string', 'maxLength': 4000}}, 'additionalProperties': False}]}}, 'processing': {'enum': ['fast', 'bulk'], 'type': 'string', 'description': 'Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit for automatic fast/bulk selection based on item × dimension decisions.'}, 'instructions': {'type': 'string', 'maxLength': 4000, 'description': 'Optional extra criteria, e.g. "judge only the service, ignore the food".'}}, 'additionalProperties': False}
classify_multi_label
Tag texts with every label that applies
Like classify_texts, but each text gets every label that applies (possibly none), with an independent 0-1 score per label. Use this for tagging — topics of an article, components touched by a ticket — where one answer is not enough. Set max_labels to cap how many come back per text. Labels scoring >= 0.7 are kept.
読み取り専用
外部アクセスあり
入力スキーマ
{'type': 'object', 'oneOf': [{'not': {'required': ['url']}, 'required': ['inputs']}, {'not': {'required': ['inputs']}, 'required': ['url']}], 'required': ['labels'], 'properties': {'url': {'type': 'string', 'pattern': '^https?://', 'maxLength': 8192, 'description': 'Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.'}, 'model': {'enum': ['jev', 'laya', 'kev', 'chunklaya'], 'type': 'string'}, 'inputs': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 1000, 'minItems': 1, 'description': '1 to 1,000 texts to classify. Results come back in the same order.'}, 'labels': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 100, 'minItems': 2, 'description': '2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.'}, 'include': {'type': 'array', 'items': {'enum': ['markdown', 'html'], 'type': 'string'}, 'description': 'With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.'}, 'max_labels': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'At most this many labels per text, most likely first.'}, 'processing': {'enum': ['fast', 'bulk'], 'type': 'string', 'description': 'Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit to select fast for up to four labels on one text, or bulk for larger work automatically.'}, 'instructions': {'type': 'string', 'description': 'Optional extra criteria, e.g. "judge only the service, ignore the food".'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['results'], 'properties': {'usage': {'type': 'object', 'properties': {'ms': {'type': 'integer'}, 'classifications': {'type': 'integer'}}}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['labels'], 'properties': {'labels': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Every label scoring >= 0.7, most likely first. May be empty.'}, 'scores': {'type': ['object', 'null'], 'description': 'Independent model preference per supplied label. Does not validate the input or guarantee correctness.', 'additionalProperties': {'type': 'number'}}}}}}}
classify_texts
Classify texts into one label each
Sort up to 1,000 texts into exactly one of your own labels each, with confidence per answer. Use this when you have many items to triage, route, filter or bucket and do not want to read them all: search results before opening them, tickets, log lines, changed files, feedback. Do not use it for fewer than about five items you can already see — just decide. For default Jev, confidence is calibrated (answers >= 0.9 are right ~82-92% of the time; < 0.5 about 30-60%); these measurements do not apply to experimental Laya. so act on the sure ones and look at the rest yourself, or pass tier "smart" to have the unsure ones re-asked of a reasoning model.
読み取り専用
外部アクセスあり
入力スキーマ
{'type': 'object', 'oneOf': [{'not': {'required': ['url']}, 'required': ['inputs']}, {'not': {'required': ['inputs']}, 'required': ['url']}], 'required': ['labels'], 'properties': {'url': {'type': 'string', 'pattern': '^https?://', 'maxLength': 8192, 'description': 'Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.'}, 'tier': {'enum': ['fast', 'smart'], 'type': 'string', 'description': 'fast (default) or smart, which re-asks answers under 0.7 confidence of a reasoning model (slower, single-label only). Independent of the Laya processing lane.'}, 'model': {'enum': ['jev', 'laya', 'kev', 'chunklaya'], 'type': 'string', 'description': "Jev is default. Default/explicit jev inputs over 32,000 characters use paid Fast-only long context: up to 250,000 original cl100k_base context tokens total, 20 documents, 32 decisions and a 1 MB body. Requires paid workspace balance or active paid subscription, not signup credit. $0.084/M original context tokens counted once across inputs, independent of dimensions. Final Jev uses selected evidence; eligible chunks may be omitted, disclosed in usage.long_context. No evidence returns 422 long_context_no_evidence without charge. Explicit 'chunklaya' retains legacy opt-in (4,000,000 characters/input, 20 inputs, subject to body limit). 'laya' (512-token context) and 'kev' (8K context) remain experimental alternatives."}, 'inputs': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 1000, 'minItems': 1, 'description': '1 to 1,000 texts to classify. Results come back in the same order.'}, 'labels': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 100, 'minItems': 2, 'description': '2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.'}, 'include': {'type': 'array', 'items': {'enum': ['markdown', 'html'], 'type': 'string'}, 'description': 'With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.'}, 'processing': {'enum': ['fast', 'bulk'], 'type': 'string', 'description': 'Optional. Implies Laya if model is omitted; has no effect with explicit Jev. With Laya, omit to select fast for one decision or bulk for batches automatically. Explicit fast accepts one decision. Shared capacity limits can return 429.'}, 'instructions': {'type': 'string', 'description': 'Optional extra criteria, e.g. "judge only the service, ignore the food".'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['results'], 'properties': {'tier': {'type': 'string'}, 'model': {'type': 'string'}, 'usage': {'type': 'object', 'properties': {'ms': {'type': 'integer'}, 'escalated': {'type': 'integer'}, 'classifications': {'type': 'integer'}}}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['label'], 'properties': {'label': {'type': 'string'}, 'scores': {'type': ['object', 'null'], 'description': 'Model preference per supplied label; sums to 1. Does not validate the input or guarantee correctness.', 'additionalProperties': {'type': 'number'}}, 'escalated': {'type': 'boolean', 'description': 'Smart tier only: this answer was re-asked of the reasoning model.'}, 'confidence': {'type': ['number', 'null'], 'description': '0-1; calibration measurements cover Jev, not experimental Laya. Null when the provider returns no score or the smart tier replaces the scored answer.'}}}, 'description': 'One per input, in input order.'}}}
count_labels
Count how many texts fall under each label
Classify up to 1,000 texts and return only a histogram: how many landed on each label, and how many the model was unsure about. Use this when you want the shape of a corpus — what share of feedback is bugs vs praise, how many search results are relevant — without pulling a thousand individual answers into context. Use classify_texts when you need the answer per item.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['inputs', 'labels'], 'properties': {'inputs': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 1000, 'minItems': 1, 'description': '1 to 1,000 texts to classify. Results come back in the same order.'}, 'labels': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 100, 'minItems': 2, 'description': '2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.'}, 'instructions': {'type': 'string', 'description': 'Optional extra criteria, e.g. "judge only the service, ignore the food".'}, 'unsure_below': {'type': 'number', 'default': 0.7, 'maximum': 1, 'minimum': 0, 'description': 'Answers with confidence under this count as unsure.'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['total', 'counts', 'unsure'], 'properties': {'total': {'type': 'integer'}, 'counts': {'type': 'object', 'description': 'Label -> how many texts, every label present.', 'additionalProperties': {'type': 'integer'}}, 'unsure': {'type': 'integer', 'description': 'How many answers fell under unsure_below.'}, 'unsure_below': {'type': 'number'}}}
review_uncertain
Find the texts the classifier was unsure about
Classify up to 1,000 texts and return only the ones whose confidence fell under a threshold (default 0.7), each with its two most likely labels. Use this after a bulk classification to decide which items deserve your own attention: the confident answers can be trusted, these are the ones to read. Returns the index of each item so you can map back to your list.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['inputs', 'labels'], 'properties': {'below': {'type': 'number', 'default': 0.7, 'maximum': 1, 'minimum': 0, 'description': 'Return items with confidence under this.'}, 'inputs': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 1000, 'minItems': 1, 'description': '1 to 1,000 texts to classify. Results come back in the same order.'}, 'labels': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 100, 'minItems': 2, 'description': '2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.'}, 'instructions': {'type': 'string', 'description': 'Optional extra criteria, e.g. "judge only the service, ignore the food".'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['total', 'uncertain'], 'properties': {'below': {'type': 'number'}, 'total': {'type': 'integer'}, 'uncertain': {'type': 'array', 'items': {'type': 'object', 'required': ['index', 'text', 'label'], 'properties': {'text': {'type': 'string'}, 'index': {'type': 'integer', 'description': 'Position in the inputs you sent.'}, 'label': {'type': 'string', 'description': "The model's best guess."}, 'runner_up': {'type': ['string', 'null'], 'description': 'The second most likely label.'}, 'confidence': {'type': ['number', 'null']}}}}}}
履歴
最近のツール変更
変更
classify_multi_label
2026年9月26日2:40
変更
classify_dimensions
2026年9月26日2:40
変更
classify_texts
2026年9月26日2:40
変更
classify_multi_label
2026年9月24日2:40
変更
classify_dimensions
2026年9月24日2:40
変更
classify_texts
2026年9月24日2:40
変更
classify_multi_label
2026年9月22日2:40
変更
classify_dimensions
2026年9月22日2:40
変更
classify_texts
2026年9月22日2:40
追加
review_uncertain
2026年9月20日2:40
追加
count_labels
2026年9月20日2:40
追加
classify_multi_label
2026年9月20日2:40
追加
classify_dimensions
2026年9月20日2:40
追加
classify_texts
2026年9月20日2:40
関連MCP
類似のMCPサーバー
LiveDataLink
io.github.blackboxfoundry/livedatalink
Exposes public-data tools covering economics, labor, banking, transport, books, legal opinions, carriers, environmental data, and…
AlpineDataWorks Intelligence Server
com.alpinedataworks/adw-intelligence-server
Provides economic, market, supply-chain, real-estate, energy, consumer, labor, and other scored intelligence indices with histori…
SharksAPI.AI
ai.sharksapi/marketing
Provides marketing analytics and actions across GA4, Search Console, Google Ads, social channels, SEO, WordPress, and marketing p…
synter-ads
io.github.Synter-Media-AI/synter-ads
Manages cross-platform advertising campaigns, audiences, tracking, creative, landing pages, campaign audits, technology intellige…
synter-ads
io.github.jshorwitz/synter-ads
Manages cross-platform advertising campaigns, audiences, tracking, creative, landing pages, campaign audits, technology intellige…
Stratalize Finance
com.stratalize/finance
Provides financial, macroeconomic, banking, credit, commodities, M&A, ESG, labor, and regulatory benchmarks for analysis and plan…
Stratalize Healthcare
com.stratalize/healthcare
Retired Stratalize server exposing benchmark, market intelligence, compliance, financial, healthcare, legal, real estate, and eco…
Stratalize Governance
com.stratalize/governance
Retired Stratalize server exposing benchmark, market intelligence, compliance, financial, healthcare, legal, real estate, and eco…