MCP MeasureMCP Measure

インデックス観測済み

Cure Cancer With AI

Free oncology data (research, trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions.

使うべきか

品質と安全性

A
説明の品質
91%
スキーマの完全性
87%
命名の品質
95%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項（2）

  • LOWTool 'predict_ppi' description lacks action verbpredict_ppi 内
  • LOWTool 'predict_clintox' description lacks action verbpredict_clintox 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~2,427トークン数（ツール定義）
~1.3 KB一般的なレスポンスサイズ
注意への影響は中程度（128k コンテキストの 1.90%）

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "cure-cancer-with-ai": {
      "url": "https://www.curecancerwithai.com/api/mcp"
    }
  }
}

リモートエンドポイント

https://www.curecancerwithai.com/api/mcpstreamable-http

できること

ツール一覧

ツール（15）

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢search_oncology(q, types, cancerType, limit)

Search a keyword across every Cure Cancer With AI dataset at once — research papers, news, blog posts, FDA approvals, and clinical trials — with results grouped by type. Use this first for broad discovery, then fetch a single record by id/slug/nctId for full detail.

入力スキーマ

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "The keyword to search for, e.g. \"osimertinib\"."
    },
    "types": {
      "type": "string",
      "description": "Optional comma-separated datasets to narrow to: research,news,blog,fdaApprovals,clinicalTrials."
    },
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Max results per dataset (1–100, default 5)."
    }
  },
  "required": [
    "q"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_research(cancerType, treatmentType, search, from, to, ...)

List peer-reviewed oncology research papers ingested from PubMed (abstracts, authors, journal, plain-language summaries). Filter by cancer type, treatment type, keyword, or publication date.

入力スキーマ

{
  "type": "object",
  "properties": {
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma."
    },
    "treatmentType": {
      "type": "string",
      "description": "Filter by treatment type."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across title and abstract."
    },
    "from": {
      "type": "string",
      "description": "ISO date lower bound (e.g. 2024-01-01)."
    },
    "to": {
      "type": "string",
      "description": "ISO date upper bound (e.g. 2024-12-31)."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_research_paper(idOrPubmedId)

Fetch a single research paper by its internal id or PubMed id.

入力スキーマ

{
  "type": "object",
  "properties": {
    "idOrPubmedId": {
      "type": "string",
      "description": "Internal id or PubMed id, e.g. \"38123456\"."
    }
  },
  "required": [
    "idOrPubmedId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_news(cancerType, search, from, to, limit, ...)

List curated cancer news articles aggregated from trusted sources. Filter by cancer type, keyword, or published date.

入力スキーマ

{
  "type": "object",
  "properties": {
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across title, summary, and content."
    },
    "from": {
      "type": "string",
      "description": "ISO date lower bound (e.g. 2024-01-01)."
    },
    "to": {
      "type": "string",
      "description": "ISO date upper bound (e.g. 2024-12-31)."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡list_blog_posts(category, cancerType, search, limit, offset)

List editorial blog articles (excerpts). Use get_blog_post for full content. Filter by category, cancer-type tag, or keyword.

入力スキーマ

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Filter by primary category."
    },
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer-type tag."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across title, excerpt, and content."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡get_blog_post(slug)

Fetch a single blog post by slug, including the full article content.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Blog post slug, e.g. \"immunotherapy-breakthroughs\"."
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_fda_approvals(cancerType, search, from, to, limit, ...)

List FDA-approved oncology drugs with indication, company, approval date, and label links. Filter by cancer type, keyword, or approval date.

入力スキーマ

{
  "type": "object",
  "properties": {
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across drug name, generic name, and indication."
    },
    "from": {
      "type": "string",
      "description": "ISO date lower bound (e.g. 2024-01-01)."
    },
    "to": {
      "type": "string",
      "description": "ISO date upper bound (e.g. 2024-12-31)."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_clinical_trials(condition, status, search, limit, offset)

List clinical trials from public registries (conditions, status, intervention type). Filter by condition, status (e.g. RECRUITING), or keyword.

入力スキーマ

{
  "type": "object",
  "properties": {
    "condition": {
      "type": "string",
      "description": "Filter by condition."
    },
    "status": {
      "type": "string",
      "description": "Filter by trial status, e.g. RECRUITING."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across title and description."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_clinical_trial(nctId)

Fetch a single clinical trial by NCT id (or internal id), including eligibility criteria and locations.

入力スキーマ

{
  "type": "object",
  "properties": {
    "nctId": {
      "type": "string",
      "description": "NCT id or internal id, e.g. \"NCT01234567\"."
    }
  },
  "required": [
    "nctId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪predict_ppi(protein_a, protein_b)

Predict the binding-affinity class for a pair of proteins using the IBM MAMMAL biomedical foundation model. Returns label "1" (interacting) or "0" (non-interacting). Inference is CPU-bound and may take up to ~60s.

入力スキーマ

{
  "type": "object",
  "properties": {
    "protein_a": {
      "type": "string",
      "description": "Amino-acid sequence, single-letter codes (ACDEFGHIKLMNPQRSTVWY), no FASTA header."
    },
    "protein_b": {
      "type": "string",
      "description": "Amino-acid sequence, single-letter codes."
    }
  },
  "required": [
    "protein_a",
    "protein_b"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪predict_dti(target_seq, drug_seq, norm_y_mean, norm_y_std)

Predict drug–target binding affinity as pKd (−log10 Kd; higher = stronger binding) using IBM MAMMAL. Inference is CPU-bound and may take up to ~60s.

入力スキーマ

{
  "type": "object",
  "properties": {
    "target_seq": {
      "type": "string",
      "description": "Target protein amino-acid sequence (single-letter codes)."
    },
    "drug_seq": {
      "type": "string",
      "description": "Drug structure in SMILES notation."
    },
    "norm_y_mean": {
      "type": "number",
      "description": "Optional normalization mean override."
    },
    "norm_y_std": {
      "type": "number",
      "description": "Optional normalization standard-deviation override."
    }
  },
  "required": [
    "target_seq",
    "drug_seq"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪predict_clintox(smiles)

Predict clinical-trial toxicity for a compound using IBM MAMMAL. Returns pred 1 (toxic / likely to fail trials) or 0 (not toxic) plus a raw score. Inference is CPU-bound and may take up to ~60s.

入力スキーマ

{
  "type": "object",
  "properties": {
    "smiles": {
      "type": "string",
      "description": "Compound structure in SMILES notation."
    }
  },
  "required": [
    "smiles"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢search_compounds(examples, preferences, limit, include_characteristics)

Find pharmaceutical compounds two ways: by example drugs you already know (fuzzy-matched), or by setting target characteristics on a −4…+4 scale. Provide exactly one of `examples` or `preferences`. Use list_compound_characteristics for the available preference names.

入力スキーマ

{
  "type": "object",
  "properties": {
    "examples": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Known drug names to find similar compounds for, e.g. [\"aspirin\",\"ibuprofen\"]. Mutually exclusive with preferences."
    },
    "preferences": {
      "type": "object",
      "additionalProperties": {
        "type": "number",
        "minimum": -4,
        "maximum": 4
      },
      "description": "Map of characteristic name to desired value on the −4…+4 scale, e.g. {\"Neuroactive\":3,\"Immunoactive\":-2}. Omit a characteristic to ignore it. Mutually exclusive with examples."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Max results (1–100, default 20)."
    },
    "include_characteristics": {
      "type": "boolean",
      "description": "Include each result’s characteristic scores in the response."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_compound_characteristics

List the pharmaceutical-compound characteristics (each scored on the −4…+4 scale) that can be used as preference keys in search_compounds.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢mammal_health

Check whether the IBM MAMMAL prediction model is loaded and ready. No API key required. Call this before predict_* tools if a prior prediction timed out.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 15 件
検証済みバージョンは記録されていませんツール 15 件
検証済みバージョンは記録されていませんツール 15 件