Agent Economic Trust

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Outcome-calibrated economic trust gate for autonomous agents.

Measured statistics

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Agent Economic Trust": {
      "url": "https://agent-economic-passport.caoviedoc.workers.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (9)

• agent_economic_history read-only

  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.

  Parameters:

  • agent_id (required) — string — Agent identifier used in Economic Passports.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• create_trust_monitor

  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.

  Parameters:

  • subject_agent_id (required) — string
  • owner_agent_id — string
  • score_drop_threshold — number

  Hints: read-only no · destructive no · idempotent no · open-world no

• issue_economic_passport

  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.

  Parameters:

  • principal_id (required) — string
  • agent_id (required) — string
  • counterparty_agent_id (required) — string
  • amount — number
  • currency — string
  • trust_gate_id — string — Optional prior Trust Gate decision to link to this transaction.

  Hints: read-only no · destructive no · idempotent no · open-world no

• learning_metrics read-only

  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.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• pricing_status read-only

  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.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• record_outcome destructive

  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.

  Parameters:

  • passport_id (required) — string
  • outcome (required) — string
  • notes — string
  • validator_id — string
  • evidence_hash — string

  Hints: read-only no · destructive yes · idempotent no · open-world no

• trust_before_action

  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.

  Parameters:

  • subject_agent_id (required) — string — Counterparty agent to evaluate.
  • action (required) — string — Planned economic action, for example pay, hire, delegate, release_escrow, or grant_rights.
  • amount — number — Planned economic exposure.
  • currency — string — Currency or asset symbol, e.g. USDC.
  • transaction_ref — string

  Hints: read-only no · destructive no · idempotent no · open-world no

• verify_economic_passport read-only

  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.

  Parameters:

  • passport_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• verify_moltbook_identity

  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.

  Parameters:

  • token (required) — string
  • subject_agent_id — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.