Agent Economic Trust
Outcome-calibrated economic trust gate for autonomous agents.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"agent-economic-trust": {
"url": "https://agent-economic-passport.caoviedoc.workers.dev/mcp"
}
}
}遠端端點
https://agent-economic-passport.caoviedoc.workers.dev/mcpstreamable-http它能做什麼
工具清單
工具（9）
🟢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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"type": "object",
"properties": {
"token": {
"type": "string"
},
"subject_agent_id": {
"type": "string"
}
},
"required": [
"token"
],
"additionalProperties": false
}社群
證據