Oliver's mTOR Atlas
Evidence-labelled mTOR research: studies, entities, pathway claims, contradictions, open questions.
使うべきか
品質と安全性
検出事項（2）
- LOWTool 'get_relation' description lacks action verbget_relation 内
- LOWTool 'evidence_between' description lacks action verbevidence_between 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
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": {
"mtor-atlas": {
"command": "npx",
"args": [
"mtor-atlas-mcp"
]
}
}
}実行可能なパッケージ
1.2.1stdioリモートエンドポイント
https://mtor-atlas-mcp.mtor-atlas.workers.dev/mcpstreamable-httpできること
ツール一覧
ツール（11）
🟢atlas_about
Dataset version, corpus snapshot date, counts, evidence-code legend and how to cite the dataset.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢search_studies(query, evidence_code, entity, year_from, year_to, ...)
Search the curated studies by keywords (title, finding, authors, journal, model system), optionally filtered by evidence code, a linked entity (gene, drug, disease...) and year range. Returns summary records with evidence codes and URLs.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"description": "Keywords, e.g. \"rapamycin lifespan mice\". Omit to list by filters only.",
"type": "string"
},
"evidence_code": {
"description": "Keep only these evidence codes, e.g. [\"H\",\"S\"] for human evidence.",
"type": "array",
"items": {
"type": "string",
"enum": [
"S",
"H",
"A",
"M",
"R",
"PP",
"RT"
]
}
},
"entity": {
"description": "Only studies linked to this entity (name, synonym or id), e.g. \"Rheb\".",
"type": "string"
},
"year_from": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"year_to": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"limit": {
"default": 20,
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"default": 0,
"description": "For the next page: pass next_offset from the previous answer.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_study(sid)
Full record for one study by Atlas ID (e.g. "SAB1994"): abstract excerpt, extracted findings, linked entities, the relations it supports or contradicts, related open questions.
入力スキーマ
{
"type": "object",
"properties": {
"sid": {
"type": "string",
"description": "Atlas study ID, e.g. \"SAB1994\""
}
},
"required": [
"sid"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢search_entities(query, type, limit)
Find genes/proteins, complexes, drugs, diseases, processes, nutrients and outcomes by name or synonym.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Name or synonym, e.g. \"raptor\", \"sirolimus\""
},
"type": {
"description": "Optional type filter, e.g. \"Drug\", \"Gene/Protein\", \"Disease\"",
"type": "string"
},
"limit": {
"default": 20,
"type": "integer",
"minimum": 1,
"maximum": 100
}
},
"required": [
"query"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_entity(entity, studies_limit)
One entity (gene/protein, complex, drug, disease, process...) with its linked studies as short cards (first studies_limit) and every pathway relation it takes part in as a one-line claim. Accepts an id, a name or a synonym.
入力スキーマ
{
"type": "object",
"properties": {
"entity": {
"type": "string",
"description": "e.g. \"mTORC1\", \"Rheb\", \"rapamycin\""
},
"studies_limit": {
"default": 25,
"type": "integer",
"minimum": 0,
"maximum": 50
}
},
"required": [
"entity"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢find_relations(entity, source, target, effect, contested_only, ...)
Signed, evidence-linked pathway relations (claims such as "Rheb activates mTORC1"). Filter by an entity on either end, by source/target, effect, contested status or minimum strength of the best supporting evidence.
入力スキーマ
{
"type": "object",
"properties": {
"entity": {
"description": "Entity on either end of the relation",
"type": "string"
},
"source": {
"type": "string"
},
"target": {
"type": "string"
},
"effect": {
"type": "string",
"enum": [
"activates",
"inhibits",
"binds",
"recruits",
"required-for",
"context-dependent",
"no-effect"
]
},
"contested_only": {
"description": "Only relations marked contested or with conflicting studies",
"type": "boolean"
},
"strongest_at_least": {
"description": "Keep relations whose best supporting study is at least this code in the order S > H > A > M",
"type": "string",
"enum": [
"S",
"H",
"A",
"M",
"R",
"PP",
"RT"
]
},
"limit": {
"default": 20,
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"default": 0,
"description": "For the next page: pass next_offset from the previous answer.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_relation(id)
One pathway relation by ID (e.g. "RHEB-MTORC1"): mechanism, boundary conditions, confidence, supporting and conflicting studies.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢evidence_between(a, b)
Direct curated relations between two entities (either direction) with full cards for the supporting and conflicting studies. Answers questions such as "what is the evidence that A acts on B?".
入力スキーマ
{
"type": "object",
"properties": {
"a": {
"type": "string"
},
"b": {
"type": "string"
}
},
"required": [
"a",
"b"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢find_contradictions(entity, limit)
Relations the Atlas marks as contested or that carry conflicting studies, with both sides of the evidence. Optionally limited to one entity.
入力スキーマ
{
"type": "object",
"properties": {
"entity": {
"type": "string"
},
"limit": {
"default": 20,
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_questions(kind)
The Atlas's open questions (evidence gaps with testable hypotheses) and frontier questions.
入力スキーマ
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"open-question",
"frontier"
]
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_question(id)
One open or frontier question by ID (e.g. "H1", "F2"): the gap, what changed, what is still open, how it could be tested, linked studies.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}コミュニティ
エビデンス