trustlayer
FeedOracle Trust Layer - 10-tool cross-server trust: signing, anchoring, verification.
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": {
"trustlayer": {
"url": "https://tooloracle.io/trust/mcp/"
}
}
}リモートエンドポイント
https://tooloracle.io/trust/mcp/streamable-httpできること
ツール一覧
ツール（10）
⚪verify_claim(claim, symbol)
Verify an agent's claim against FeedOracle signed evidence. Checks if a statement (e.g. 'USDC market cap is $32B') matches live, cryptographically signed data. Returns verified/partially_verified/unverified with confidence score and recommended action.
入力スキーマ
{
"type": "object",
"properties": {
"claim": {
"type": "string",
"description": "The claim to verify, e.g. 'USDC has $32B market cap'"
},
"symbol": {
"type": "string",
"description": "Token symbol (auto-detected from claim if omitted)"
}
},
"required": [
"claim"
],
"additionalProperties": false
}🟢get_signed_fact(symbol, fact_type)
WITHDRAWN (2026-08-09). This tool does not produce or verify a cryptographic signature and returns a non-success withdrawal notice. Do not rely on it for signed evidence.
入力スキーマ
{
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "Token symbol: USDC, RLUSD, EURC, USDT, DAI",
"enum": [
"USDC",
"RLUSD",
"EURC",
"USDT",
"DAI"
]
},
"fact_type": {
"type": "string",
"description": "Type: price, peg, market_cap, reserve",
"default": "price"
}
},
"required": [
"symbol"
],
"additionalProperties": false
}⚪provenance_trace(symbol)
Full data provenance chain — traces every data point from external source (CoinGecko, ESMA, on-chain) through FeedOracle processing to final delivery. Each step individually hashed. Supports EU AI Act Art. 13 transparency requirements.
入力スキーマ
{
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "Token symbol to trace"
}
},
"required": [
"symbol"
],
"additionalProperties": false
}🟢freshness_guard(symbol, max_age_seconds)
Check if data is current, stale, or expired. Prevents agent decisions based on outdated information. Configurable max age threshold.
入力スキーマ
{
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "Token symbol (optional — checks overall feed if omitted)"
},
"max_age_seconds": {
"type": "integer",
"description": "Maximum acceptable age in seconds (default: 300)",
"default": 300
}
},
"additionalProperties": false
}🟢hallucination_check(statement, context)
Compare an agent's statement against ground truth evidence. Detects factual mismatches and dangerous hallucination patterns (absolute language, suspect claims). Returns evidence checks and red flags.
入力スキーマ
{
"type": "object",
"properties": {
"statement": {
"type": "string",
"description": "The statement to check against evidence"
},
"context": {
"type": "string",
"description": "Optional context for the statement"
}
},
"required": [
"statement"
],
"additionalProperties": false
}⚪verify_signature(jws, content_hash)
WITHDRAWN (2026-08-09). This tool performs no cryptographic signature verification and returns a non-success withdrawal notice. A hash comparison is not signature verification.
入力スキーマ
{
"type": "object",
"properties": {
"jws": {
"type": "string",
"description": "JWS token to verify"
},
"content_hash": {
"type": "string",
"description": "Content hash to verify (sha256:...)"
}
},
"additionalProperties": false
}⚪confidence_gate(symbol, action_type, min_confidence)
Decision gate for agents: should I proceed, exercise caution, abstain, or escalate? Evaluates multi-factor confidence for a specific action type (cite, trade, report, recommend) against a threshold.
入力スキーマ
{
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "Token to evaluate"
},
"action_type": {
"type": "string",
"description": "What the agent wants to do: cite, trade, report, recommend",
"default": "cite"
},
"min_confidence": {
"type": "integer",
"description": "Minimum confidence to proceed (0-100, default: 70)",
"default": 70,
"minimum": 0,
"maximum": 100
}
},
"required": [
"symbol"
],
"additionalProperties": false
}🟡evidence_anchor(fact, symbol, framework)
WITHDRAWN (2026-08-09). This tool does not submit any blockchain transaction and creates no on-chain anchor or proof; it returns a non-success withdrawal notice.
入力スキーマ
{
"type": "object",
"properties": {
"fact": {
"type": "string",
"description": "The fact to anchor"
},
"symbol": {
"type": "string",
"description": "Related token symbol (optional)"
},
"framework": {
"type": "string",
"description": "Framework context: trust_layer, mica, dora",
"default": "trust_layer"
}
},
"required": [
"fact"
],
"additionalProperties": false
}🟢agent_reputation(client_id, agent_name)
Get trust score and reputation for an AI agent from FeedOracle KYA (Know Your Agent) system. Returns trust level (UNVERIFIED → CERTIFIED), score (0-100), and registration details.
入力スキーマ
{
"type": "object",
"properties": {
"client_id": {
"type": "string",
"description": "Agent's client_id from KYA registration"
},
"agent_name": {
"type": "string",
"description": "Agent name to search (if client_id unknown)"
}
},
"additionalProperties": false
}⚪trust_status
Trust Layer infrastructure health, capabilities, and component status. Shows which verification services are online and what the Trust Layer can do.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}コミュニティ
エビデンス