executable-science
Read-only research pilot catalogue: task templates, resources, starter studies, capability status.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'platform_status' description lacks action verbplatform_status 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": {
"executable-science": {
"url": "https://executable.science/api/mcp"
}
}
}リモートエンドポイント
https://executable.science/api/mcpstreamable-httpできること
ツール一覧
ツール（8）
🟢get_resource(resource_id)
Read one catalogued public resource by its identifier, including its recorded rights and provenance.
入力スキーマ
{
"type": "object",
"properties": {
"resource_id": {
"type": "string",
"description": "Catalogue identifier."
}
},
"required": [
"resource_id"
],
"additionalProperties": false
}🟢get_starter_source(study_id)
Download one original licensed starter ZIP as base64 with its SHA-256 and rights. Source has not run or been verified; submitting it still requires isolated ingestion.
入力スキーマ
{
"type": "object",
"properties": {
"study_id": {
"type": "string"
}
},
"required": [
"study_id"
],
"additionalProperties": false
}🟢get_starter_study(study_id)
Read one licensed starter study's frozen inputs, archive digest, environment, expected interpretation and unrun status.
入力スキーマ
{
"type": "object",
"properties": {
"study_id": {
"type": "string"
}
},
"required": [
"study_id"
],
"additionalProperties": false
}🟢get_task_template(task_id)
Read one frozen task template in full: its question, inputs, assumptions, comparison basis, stated limitations and revision digest. The digest pins the exact revision an attempt was prepared against.
入力スキーマ
{
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task template identifier."
}
},
"required": [
"task_id"
],
"additionalProperties": false
}🟢list_starter_studies
List original downloadable source studies with explicit licenses, archive digests, pinned catalog environments and unrun evidence status.
入力スキーマ
{
"type": "object",
"additionalProperties": false
}🟢list_task_templates
List the bounded, frozen questions this platform publishes for attempt. Each carries a revision digest and its own stated limitations.
入力スキーマ
{
"type": "object",
"additionalProperties": false
}⚪platform_status
Report the current stage and, for every capability, whether it is available and the stated reason. Several capabilities are gated; this tool is the authoritative answer on which.
入力スキーマ
{
"type": "object",
"additionalProperties": false
}🟢search_resources(query, kind, limit)
Search the public catalogue of datasets, software packages, published articles, method references and original experiments by title.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Words matched against titles."
},
"kind": {
"type": "string",
"enum": [
"dataset",
"software_package",
"published_article",
"method_reference",
"original_experiment"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
}
},
"additionalProperties": false
}コミュニティ
エビデンス