Skip to content

Agent Economic Trust

by agent-economic-passport.caoviedoc.workers.dev · remote · no sign-in to list tools · v0.3.0 · published by dev.workers.caoviedoc.agent-economic-passport

Outcome-calibrated economic trust gate for autonomous agents.

Deletes · 1Final · 2Changes · 2
CompareRegistry entry

9 tools: 1 can delete or cancel things, 2 do something that can't be undone, 2 change things and 4 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agent-economic-trust https://agent-economic-passport.caoviedoc.workers.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

9 tools

Deletes or cancels 1Claude Code: deny
  • record_outcomeAppend the final observed outcome to an Economic Passport.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
    • idempotentHint: false
Can't be undone 2Claude Code: ask
  • issue_economic_passportCreate an append-only Economic Passport recording the parties and economic context of one agent-to-agent transaction.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    • The input carries an amount (input.amount) and a currency, so it moves money.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: false
  • trust_before_actionEvaluate an agent counterparty before an irreversible economic action such as paying, hiring, delegating, releasing escrow, or granting rights.No findings

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    • The description says "irreversible".
    • The input carries an amount (input.amount) and a currency, so it moves money.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: false
Changes things 2Claude Code: ask
  • create_trust_monitorCreate continuous monitoring for one agent counterparty.No findings

    Why it is in this group

    • The name "create_trust_monitor" says "create": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: false
  • verify_moltbook_identityVerify a temporary Moltbook identity token and bind the verified assertion to an agent identifier.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: false
Only reads 4Claude Code: allow
  • agent_economic_historyRead the economic history observed by this registry for a specific autonomous agent.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • learning_metricsRead model calibration, labeled outcomes, false-ALLOW rate, regression results, discovery metrics, monitors, and verified revenue.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • pricing_statusRead the current pricing and x402 activation state.No findings

    Why it is in this group

    • The name "pricing_status" says "status": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • verify_economic_passportRetrieve and verify an Economic Passport and its immutable outcome history.No findings

    Why it is in this group

    • The description's first verb is "retrieve": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-economic-trust https://agent-economic-passport.caoviedoc.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-economic-trust__agent_economic_history",
      "mcp__agent-economic-trust__learning_metrics",
      "mcp__agent-economic-trust__pricing_status",
      "mcp__agent-economic-trust__verify_economic_passport"
    ],
    "ask": [
      "mcp__agent-economic-trust__create_trust_monitor",
      "mcp__agent-economic-trust__issue_economic_passport",
      "mcp__agent-economic-trust__trust_before_action",
      "mcp__agent-economic-trust__verify_moltbook_identity"
    ],
    "deny": [
      "mcp__agent-economic-trust__record_outcome"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agent-economic-trust. Review it before you use it.