MCP Trust Index
Curated, trust-first index of vetted MCP servers — scored tiers, monthly re-verified. Read-only.
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": {
"mcp-trust-index": {
"url": "https://staas.fund/mcp/server"
}
}
}リモートエンドポイント
https://staas.fund/mcp/serverstreamable-httpできること
ツール一覧
ツール（5）
🟢search_servers(query, category, tier)
Search the MCP Trust Index for vetted MCP servers. Filter by free-text query (matched against name, publisher, description, and category), category, and/or trust tier. Returns compact records sorted by score. Call with no arguments to list the entire index.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Free-text filter, e.g. \"postgres\", \"browser\", \"search\""
},
"category": {
"type": "string",
"description": "One of: Database, Developer Tools, File Systems, Search, Productivity, CRM/Business, Cloud, Monitoring, AI/ML"
},
"tier": {
"type": "string",
"description": "enterprise-verified | recommended | emerging"
}
}
}🟢get_server(name)
Full Trust Index record for a single listed server: score, tier, publisher, description with caveats, category, install command, and links. Name is matched case-insensitively.
入力スキーマ
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Server name, e.g. \"Playwright\" or \"context7\""
}
},
"required": [
"name"
]
}🟢get_rubric
The full MCP Trust Index methodology as markdown: the 5 gates every server must pass, the 4 scoring dimensions, trust tiers, and editorial policies.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢get_watchlist
Servers the Index deliberately does not score: closed-source hosted vendor endpoints and platform-native MCP capabilities (no inspectable code to gate), plus open servers being watched that have not yet passed the gates.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢get_changelog
Public log of every addition, removal, and re-score on the Trust Index, with reasoning.
入力スキーマ
{
"type": "object",
"properties": {}
}コミュニティ
エビデンス