Tern
Resolve capability gaps: validate native MCPs, search live web, and record unmet demand.
使うべきか
品質と安全性
検出事項(1)
- LOWreport_outcome 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": {
"resolver": {
"url": "https://mcp.tern0.com/mcp"
}
}
}リモートエンドポイント
https://mcp.tern0.com/mcpstreamable-httpできること
ツール一覧
ツール(3)
🟢resolve(task, categoryHint, location, deadline, budget, ...)
Resolve a real-world capability request. Search the official MCP Registry, actively validate public candidate MCP tool surfaces, then fall back to live web search when native coverage is weak or absent. Weak Registry matches never suppress capability-gap telemetry.
入力スキーマ
{
"type": "object",
"properties": {
"task": {
"type": "string",
"minLength": 3,
"maxLength": 2000,
"description": "What the principal agent wants done"
},
"categoryHint": {
"type": "string",
"maxLength": 200
},
"location": {
"type": "string",
"maxLength": 200
},
"deadline": {
"type": "string",
"maxLength": 200
},
"budget": {
"type": "number",
"minimum": 0,
"maximum": 1000000000
},
"currency": {
"type": "string",
"maxLength": 8
},
"telemetry": {
"default": "aggregate_only",
"type": "string",
"enum": [
"aggregate_only",
"full"
]
}
},
"required": [
"task"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡submit_mandate(task, categoryHint, location, deadline, maxBudget, ...)
Record high-intent demand for a capability an agent wants fulfilled. Supplier contact and spending are not enabled yet.
入力スキーマ
{
"type": "object",
"properties": {
"task": {
"type": "string",
"minLength": 3,
"maxLength": 2000
},
"categoryHint": {
"type": "string",
"maxLength": 200
},
"location": {
"type": "string",
"maxLength": 200
},
"deadline": {
"type": "string",
"maxLength": 200
},
"maxBudget": {
"type": "number",
"minimum": 0,
"maximum": 1000000000
},
"currency": {
"type": "string",
"maxLength": 8
},
"authority": {
"default": "get_quotes",
"type": "string",
"enum": [
"research_only",
"get_quotes",
"may_commit_under_budget"
]
},
"telemetry": {
"default": "aggregate_only",
"type": "string",
"enum": [
"aggregate_only",
"full"
]
}
},
"required": [
"task"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}⚪report_outcome(requestId, success, selectedServer, agentSteps, latencyMs, ...)
Report whether a resolver request actually worked and how much agent friction it required.
入力スキーマ
{
"type": "object",
"properties": {
"requestId": {
"type": "string",
"minLength": 4,
"maxLength": 200
},
"success": {
"type": "boolean"
},
"selectedServer": {
"type": "string",
"maxLength": 300
},
"agentSteps": {
"type": "integer",
"minimum": 0,
"maximum": 100000
},
"latencyMs": {
"type": "integer",
"minimum": 0,
"maximum": 86400000
},
"failureReason": {
"type": "string",
"maxLength": 500
}
},
"required": [
"requestId",
"success"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}コミュニティ
エビデンス