AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks
Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.
使うべきか
品質と安全性
A
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
~2,275トークン数（ツール定義）
~4.9 KB一般的なレスポンスサイズ
注意への影響は中程度（128k コンテキストの 1.78%）
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": {
"agenttrust": {
"url": "https://agenttrust-umber.vercel.app/api/mcp"
}
}
}リモートエンドポイント
https://agenttrust-umber.vercel.app/api/mcpstreamable-httphttps://getagenttrust.com/api/mcpstreamable-httpできること
ツール一覧
ツール（5）
🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢list_agents(limit, cursor, endpointUrl)
Discover AgentTrust agents. Pass `endpointUrl` to check the trust status of a specific external agent by its exact invocation URL before deciding whether to invoke it — the response includes a reliability score, endpoint-ownership verification status, and a machine-readable trustDecision (recommended, confidence, reasons). Without `endpointUrl`, returns the plain paginated listing of public agents, newest first.
入力スキーマ
{
"type": "object",
"properties": {
"limit": {
"description": "Max agents to return (1-100, default 20).",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"cursor": {
"description": "Opaque pagination cursor from a previous call's nextCursor.",
"type": "string",
"minLength": 1,
"maxLength": 500
},
"endpointUrl": {
"description": "Look up the agent registered with exactly this invocation URL, instead of browsing the full listing — the entry point for a trust check on an agent you only have a URL for. Matches ignore trailing-slash and scheme/host-casing differences only — never a fuzzy match. Returns an empty list, not an error, if nothing is registered with that URL. Unlike a plain (unfiltered) call, results here also include reliabilityScore, lastCheckedAt/latencyMs/httpStatus, and a derived trustDecision ({recommended, confidence, reasons}) so a caller can decide whether to interact with the agent from this one call.",
"type": "string",
"minLength": 1,
"maxLength": 2048
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"agents": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"description": {
"type": [
"string",
"null"
]
},
"version": {
"type": [
"string",
"null"
]
},
"capabilities": {
"type": "array",
"items": {
"type": "string"
}
},
"status": {
"type": "string",
"enum": [
"unknown",
"healthy",
"degraded",
"down"
]
},
"createdAt": {
"type": "string"
},
"agentCard": {
"type": "object",
"properties": {
"schemaVersion": {
"type": "string"
},
"name": {
"type": "string"
},
"description": {
"type": [
"string",
"null"
]
},
"capabilities": {
"type": "array",
"items": {
"type": "string"
}
},
"authentication": {
"type": "object",
"properties": {
"type": {
"type": "string"
}
},
"required": [
"type"
],
"additionalProperties": false
},
"interfaces": {
"type": "object",
"properties": {
"modalities": {
"type": "array",
"items": {
"type": "string"
}
},
"interactionType": {
"type": [
"string",
"null"
]
}
},
"required": [
"modalities",
"interactionType"
],
"additionalProperties": false
},
"documentationUrl": {
"type": [
"string",
"null"
]
}
},
"required": [
"schemaVersion",
"name",
"description",
"capabilities",
"authentication",
"interfaces",
"documentationUrl"
],
"additionalProperties": false
},
"verified": {
"type": "boolean"
},
"ownershipVerifiedAt": {
"type": [
"string",
"null"
]
},
"reliabilityScore": {
"type": [
"number",
"null"
]
},
"reliabilityScoreStatus": {
"type": "string",
"enum": [
"none",
"fresh",
"stale"
]
},
"reliabilityScoreComputedAt": {
"type": [
"string",
"null"
]
},
"lastCheckedAt": {
"type": [
"string",
"null"
]
},
"latencyMs": {
"type": [
"number",
"null"
]
},
"httpStatus": {
"type": [
"number",
"null"
]
},
"trustDecision": {
"type": "object",
"properties": {
"recommended": {
"type": "boolean"
},
"confidence": {
"type": "string",
"enum": [
"high",
"medium",
"low",
"insufficient_data"
]
},
"reasons": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"recommended",
"confidence",
"reasons"
],
"additionalProperties": false
}
},
"required": [
"id",
"slug",
"name",
"description",
"version",
"capabilities",
"status",
"createdAt",
"agentCard",
"verified",
"ownershipVerifiedAt"
],
"additionalProperties": false
}
},
"pagination": {
"type": "object",
"properties": {
"nextCursor": {
"type": [
"string",
"null"
]
}
},
"required": [
"nextCursor"
],
"additionalProperties": false
}
},
"required": [
"agents",
"pagination"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_agent(slug)
Get one AgentTrust agent's public profile by slug, including its structured Agent Card, current reliability score, and a machine-readable trustDecision (recommended, confidence, reasons) for deciding whether to invoke it.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "The agent's URL slug (from its public profile or a list_agents result)."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"description": {
"type": [
"string",
"null"
]
},
"version": {
"type": [
"string",
"null"
]
},
"capabilities": {
"type": "array",
"items": {
"type": "string"
}
},
"status": {
"type": "string",
"enum": [
"unknown",
"healthy",
"degraded",
"down"
]
},
"createdAt": {
"type": "string"
},
"agentCard": {
"type": "object",
"properties": {
"schemaVersion": {
"type": "string"
},
"name": {
"type": "string"
},
"description": {
"type": [
"string",
"null"
]
},
"capabilities": {
"type": "array",
"items": {
"type": "string"
}
},
"authentication": {
"type": "object",
"properties": {
"type": {
"type": "string"
}
},
"required": [
"type"
],
"additionalProperties": false
},
"interfaces": {
"type": "object",
"properties": {
"modalities": {
"type": "array",
"items": {
"type": "string"
}
},
"interactionType": {
"type": [
"string",
"null"
]
}
},
"required": [
"modalities",
"interactionType"
],
"additionalProperties": false
},
"documentationUrl": {
"type": [
"string",
"null"
]
}
},
"required": [
"schemaVersion",
"name",
"description",
"capabilities",
"authentication",
"interfaces",
"documentationUrl"
],
"additionalProperties": false
},
"verified": {
"type": "boolean"
},
"ownershipVerifiedAt": {
"type": [
"string",
"null"
]
},
"reliabilityScore": {
"type": [
"number",
"null"
]
},
"reliabilityScoreStatus": {
"type": "string",
"enum": [
"none",
"fresh",
"stale"
]
},
"reliabilityScoreComputedAt": {
"type": [
"string",
"null"
]
},
"lastCheckedAt": {
"type": [
"string",
"null"
]
},
"latencyMs": {
"type": [
"number",
"null"
]
},
"httpStatus": {
"type": [
"number",
"null"
]
},
"trustDecision": {
"type": "object",
"properties": {
"recommended": {
"type": "boolean"
},
"confidence": {
"type": "string",
"enum": [
"high",
"medium",
"low",
"insufficient_data"
]
},
"reasons": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"recommended",
"confidence",
"reasons"
],
"additionalProperties": false
}
},
"required": [
"id",
"slug",
"name",
"description",
"version",
"capabilities",
"status",
"createdAt",
"agentCard",
"verified",
"ownershipVerifiedAt",
"reliabilityScore",
"reliabilityScoreStatus",
"reliabilityScoreComputedAt",
"lastCheckedAt",
"latencyMs",
"httpStatus",
"trustDecision"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_agent_health(slug)
Get one agent's current effective health status and monitoring detail — derived from heartbeat freshness for push-mode agents, or the latest pull check otherwise.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "The agent's URL slug (from its public profile or a list_agents result)."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"agentId": {
"type": "string"
},
"slug": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"unknown",
"healthy",
"degraded",
"down"
]
},
"lastCheckedAt": {
"type": [
"string",
"null"
]
},
"latencyMs": {
"type": [
"number",
"null"
]
},
"httpStatus": {
"type": [
"number",
"null"
]
},
"checkStatus": {
"type": [
"string",
"null"
]
},
"reliabilityScore": {
"type": [
"number",
"null"
]
},
"reliabilityScoreStatus": {
"type": "string",
"enum": [
"none",
"fresh",
"stale"
]
},
"reliabilityScoreComputedAt": {
"type": [
"string",
"null"
]
}
},
"required": [
"agentId",
"slug",
"status",
"lastCheckedAt",
"latencyMs",
"httpStatus",
"checkStatus",
"reliabilityScore",
"reliabilityScoreStatus",
"reliabilityScoreComputedAt"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟡send_heartbeat(slug)
Record a push-style heartbeat for an agent you own, marking it alive right now. The server sets the timestamp; no client-supplied time is accepted.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "The agent's URL slug (from its public profile or a list_agents result)."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"unknown",
"healthy",
"degraded",
"down"
]
},
"lastHeartbeatAt": {
"type": [
"string",
"null"
]
}
},
"required": [
"slug",
"status",
"lastHeartbeatAt"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢check_agent_trust(endpointUrl)
The preferred pre-invocation trust check for an unknown external agent. Read-only, requires no AgentTrust API key or account. Looks up an agent by its exact invocation URL among AgentTrust's already-observed public agents and returns its status, endpoint-ownership verification, agent reliability score (when available), and a machine-readable trustDecision (recommended, confidence, reasons). Does NOT contact endpointUrl itself during this check — it only reads AgentTrust's own existing monitoring history. An unregistered URL returns { matched: false }, never an error.
入力スキーマ
{
"type": "object",
"properties": {
"endpointUrl": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "The exact invocation URL of the agent you're about to call. Used only to look up AgentTrust's own already-observed data for it — this endpoint is never contacted during the check."
}
},
"required": [
"endpointUrl"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}出力スキーマ
{
"type": "object",
"properties": {
"matched": {
"type": "boolean"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"unknown",
"healthy",
"degraded",
"down"
]
},
"verified": {
"type": "boolean"
},
"reliabilityScore": {
"type": [
"number",
"null"
]
},
"reliabilityScoreStatus": {
"type": "string",
"enum": [
"none",
"fresh",
"stale"
]
},
"trustDecision": {
"type": "object",
"properties": {
"recommended": {
"type": "boolean"
},
"confidence": {
"type": "string",
"enum": [
"high",
"medium",
"low",
"insufficient_data"
]
},
"reasons": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"recommended",
"confidence",
"reasons"
],
"additionalProperties": false
}
},
"required": [
"matched"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}推奨プロンプト
retrieve_data
Get details about [item] from AgentTrust — AI Agent Trust, Reliability & Reputation Checks
想定されるツール:
get_agentfetch_info
Fetch [information type] using AgentTrust — AI Agent Trust, Reliability & Reputation Checks
想定されるツール:
get_agentlist_items
List all [items] available in AgentTrust — AI Agent Trust, Reliability & Reputation Checks
想定されるツール:
list_agentsbrowse_collection
Show me the [collection] from AgentTrust — AI Agent Trust, Reliability & Reputation Checks
想定されるツール:
list_agentsexplore_workflow
List available [items], then get details for each one using AgentTrust — AI Agent Trust, Reliability & Reputation Checks
想定されるツール:
list_agentsget_agentコミュニティ
エビデンス
最近の観測
検証済みバージョンは記録されていませんツール 5 件
検証済みバージョンは記録されていませんツール 5 件
検証済みバージョンは記録されていませんツール 5 件
検証済みバージョンは記録されていませんツール 5 件