Jason Lovell
Read-only tools for Jason Lovell's AI research: studies, builds, releases, search and contact.
使うべきか
品質と安全性
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": {
"site": {
"url": "https://jasonlovell.ai/mcp"
}
}
}リモートエンドポイント
https://jasonlovell.ai/mcpstreamable-httpできること
ツール一覧
ツール（8）
🟢get_profile
Who Jason Lovell is: day role, career from mobile through Samsung, Captivate and PwC, how he builds, what he cares about now, and how to reach him.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢list_studies(question)
The ten research studies: each one's question, kind of result, a short outcome, date and page. Can filter by the question a study asks.
入力スキーマ
{
"type": "object",
"properties": {
"question": {
"description": "Only studies asking this question.",
"type": "string",
"enum": [
"Does the state hold up?",
"Can we trust the score?",
"What carries over?",
"Where does judgment sit?"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_study(slug)
One study in full: the question, the result, the design decision, what was recorded, the evidence links and where the evidence stops.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"enum": [
"mcp-continuation-replay",
"scaffold-arena",
"realitybridge",
"shadowskillbench",
"living-context",
"jev-decision-lab",
"ghosttrace",
"no-model-floor",
"cascadeshift",
"nano-interpretability"
],
"description": "The study's slug, from list_studies."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_builds
Public repositories by area, newest first.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢get_build(slug)
One build: what it is and includes, and for builds with a design record, the question it answers, the design choice and where it stops.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"enum": [
"personal-ai-sovereignty-lab",
"agent-assurance-case",
"damn-vulnerable-agent-asset-corpus",
"nanoassembly",
"ghosttrace",
"proofpack",
"branchlab",
"baton-studio",
"meta-memory-studio",
"agent-director",
"scaffold-arena",
"proofkern",
"nanoim",
"nanoawm",
"nanocircuits",
"nanofeatures",
"skillscope",
"sentinel-mcp",
"amdm",
"switchboard",
"mcp-interop-bakeoff",
"agent-hq-guard",
"overhearops",
"skillcheck",
"rlm-lens",
"runwright",
"agentgate",
"terrisk-agent",
"voiceforge-ai",
"skillbench-pd",
"agent-ready-checkout-gateway"
],
"description": "The build's slug."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_releases
Specifications, a white paper and research software, with DOIs where they have them.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢search_site(query)
Find studies, builds and releases by keyword.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 120
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢contact_routes
Ways to reach Jason, by purpose. It sends nothing: pass the route to the person you act for.
入力スキーマ
{
"type": "object",
"properties": {}
}コミュニティ
エビデンス