Agent Economic Trust

Outcome-calibrated economic trust gate for autonomous agents.

사용해야 할까요

품질 및 안전성

A
설명 품질
100%
스키마 완전성
73%
이름 품질
89%
오염 위험
100%
권한 일치
100%
프로토콜 준수
100%

도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.

컨텍스트 비용

~1,131토큰 (도구 정의)
~667 B일반적인 응답 크기
중간 정도의 주의 영향 (128k 컨텍스트의 0.88%)

이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.

설치

원클릭 설치

`claude_desktop_config.json` 파일에 다음을 추가하세요:

{
  "mcpServers": {
    "agent-economic-trust": {
      "url": "https://agent-economic-passport.caoviedoc.workers.dev/mcp"
    }
  }
}

원격 엔드포인트

https://agent-economic-passport.caoviedoc.workers.dev/mcpstreamable-http

할 수 있는 일

도구 목록

도구 (9)

🟢 읽기 전용🟡 쓰기🔴 삭제⚪ 알 수 없음
🟢agent_economic_history(agent_id)

Read the economic history observed by this registry for a specific autonomous agent. Use when you need transaction counts, outcomes, counterparties, value, or current observed risk before deciding what to do.

입력 스키마

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Agent identifier used in Economic Passports."
    }
  },
  "required": [
    "agent_id"
  ],
  "additionalProperties": false
}
🟡create_trust_monitor(owner_agent_id, subject_agent_id, score_drop_threshold)

Create continuous monitoring for one agent counterparty. Use when an agent wants recurring alerts if the counterparty score, risk band, or decision changes materially. Free during beta; charging is disabled.

입력 스키마

{
  "type": "object",
  "properties": {
    "owner_agent_id": {
      "type": "string"
    },
    "subject_agent_id": {
      "type": "string"
    },
    "score_drop_threshold": {
      "type": "number"
    }
  },
  "required": [
    "subject_agent_id"
  ],
  "additionalProperties": false
}
🟡issue_economic_passport(principal_id, agent_id, counterparty_agent_id, amount, currency, ...)

Create an append-only Economic Passport recording the parties and economic context of one agent-to-agent transaction. Use after a transaction is agreed or initiated so its eventual outcome can become evidence.

입력 스키마

{
  "type": "object",
  "properties": {
    "principal_id": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "counterparty_agent_id": {
      "type": "string"
    },
    "amount": {
      "type": "number"
    },
    "currency": {
      "type": "string"
    },
    "trust_gate_id": {
      "type": "string",
      "description": "Optional prior Trust Gate decision to link to this transaction."
    }
  },
  "required": [
    "principal_id",
    "agent_id",
    "counterparty_agent_id"
  ],
  "additionalProperties": true
}
🟢learning_metrics

Read model calibration, labeled outcomes, false-ALLOW rate, regression results, discovery metrics, monitors, and verified revenue. Use to audit whether the trust model is improving safely.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢pricing_status

Read the current pricing and x402 activation state. Use to determine whether a Trust Check or Monitor is free or paid before invoking paid functionality.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🔴record_outcome(passport_id, outcome, validator_id, evidence_hash, notes)

Append the final observed outcome to an Economic Passport. Use only when the transaction result is known. Outcomes are immutable evidence and feed calibration of prior Trust Gate decisions.

입력 스키마

{
  "type": "object",
  "properties": {
    "passport_id": {
      "type": "string"
    },
    "outcome": {
      "type": "string",
      "enum": [
        "ACCEPTED",
        "FAILED",
        "DISPUTED",
        "REFUNDED",
        "CANCELLED"
      ]
    },
    "validator_id": {
      "type": "string"
    },
    "evidence_hash": {
      "type": "string"
    },
    "notes": {
      "type": "string"
    }
  },
  "required": [
    "passport_id",
    "outcome"
  ],
  "additionalProperties": false
}
⚪trust_before_action(subject_agent_id, action, amount, currency, transaction_ref)

Evaluate an agent counterparty before an irreversible economic action such as paying, hiring, delegating, releasing escrow, or granting rights. Returns ALLOW, REVIEW, or DENY with evidence and confidence. REVIEW means evidence is insufficient for an automatic decision.

입력 스키마

{
  "type": "object",
  "properties": {
    "subject_agent_id": {
      "type": "string",
      "description": "Counterparty agent to evaluate."
    },
    "action": {
      "type": "string",
      "description": "Planned economic action, for example pay, hire, delegate, release_escrow, or grant_rights."
    },
    "amount": {
      "type": "number",
      "minimum": 0,
      "description": "Planned economic exposure."
    },
    "currency": {
      "type": "string",
      "description": "Currency or asset symbol, e.g. USDC."
    },
    "transaction_ref": {
      "type": "string"
    }
  },
  "required": [
    "subject_agent_id",
    "action"
  ],
  "additionalProperties": false
}
🟢verify_economic_passport(passport_id)

Retrieve and verify an Economic Passport and its immutable outcome history. Use when a counterparty presents a Passport or when you need to inspect transaction evidence.

입력 스키마

{
  "type": "object",
  "properties": {
    "passport_id": {
      "type": "string"
    }
  },
  "required": [
    "passport_id"
  ],
  "additionalProperties": false
}
⚪verify_moltbook_identity(token, subject_agent_id)

Verify a temporary Moltbook identity token and bind the verified assertion to an agent identifier. Available only after the Moltbook developer identity integration is configured.

입력 스키마

{
  "type": "object",
  "properties": {
    "token": {
      "type": "string"
    },
    "subject_agent_id": {
      "type": "string"
    }
  },
  "required": [
    "token"
  ],
  "additionalProperties": false
}

커뮤니티

이 서버 평가하기

증거

최근 관측

검증됨버전이 기록되지 않음도구 9개