Screwtape.ai

Descrizione

Screwtape.ai è un controllo indipendente sull’output degli agenti AI. Valuta una singola bozza di risposta rispetto alle prove fornite, calcola il grado di accordo tra 2 e 16 risposte per segnalare falsi consensi e controlla se le fatture sono duplicate prima che un agente le paghi. I risultati positivi possono includere una ricevuta firmata Ed25519, e la ricevuta può essere pubblicata come badge di verifica.

Funziona come endpoint Streamable HTTP ospitato all’indirizzo https://screwtape.ai/mcp. Le chiamate usano una chiave API Bearer (una chiave gratuita consente 100 chiamate per giorno UTC) oppure un pagamento per chiamata di 0,005 $ in USDC su Base o Solana tramite x402. Il contenuto valutato non viene salvato, a meno che retain non sia impostato su true.

Cosa puoi fare

• Ottenere un verdetto pass, fail o retry sull’output di un agente rispetto alle prove
• Controllare se una fattura è duplicata prima che un agente la paghi
• Calcolare il falso consenso tra 2 e 16 risposte
• Creare una chiave API gratuita tramite una registrazione con proof of work
• Ottenere i requisiti di pagamento per i pacchetti di chiamate prepagati
• Pubblicare una ricevuta firmata come badge pubblico di verifica

Tool 9

• budget_ledgerScrive

  Budget Ledger

• action_receiptScrive

  Action Receipts

• payment_checkSola lettura

  Payment check

• judgeSola lettura

  Restituisce un verdetto pass, fail o retry sull’output di un agente, verificato rispetto alle prove fornite.

• check_duplicate_invoiceScrive

  Valuta una fattura e la confronta con le fatture registrate in precedenza per segnalare se è duplicata.

• consensusSola lettura

  Calcola l’accordo tra 2 e 16 risposte e segnala consensi copiati o poco solidi.

• get_api_keyScrive

  Crea una chiave API gratuita (100 chiamate per giorno UTC) con una proof of work SHA-256.

• publish_receiptScrive

  Pubblica una ricevuta firmata di tua proprietà come pagina badge pubblica Screwtape Verified.

• try_checkSola lettura

  Try one sample duplicate-invoice check (free, no key)

Letti dal server attivo (15 nov 2026). Sola lettura, Scrive e Può eliminare sono indicazioni dichiarate dal server; è il tuo client a decidere se chiederti conferma prima di eseguire un tool.

Prompt di esempio

• Controlla se questa fattura è duplicata prima di pagarla.

• Valuta la mia bozza di risposta rispetto a queste prove e dimmi se è approvata.

• Esegui un controllo del consenso su queste cinque risposte degli agenti.

• Pubblica come badge la ricevuta dell’ultimo verdetto.

Configurazione

Ogni client si collega a screwtape.ai. Scegli il tuo; la pagina ricorda la tua scelta.

claude mcp add --transport http screwtape-ai https://screwtape.ai/mcp

https://screwtape.ai/mcp

{
  "mcpServers": {
    "screwtape-ai": {
      "url": "https://screwtape.ai/mcp"
    }
  }
}

code --add-mcp '{"name":"screwtape-ai","type":"http","url":"https://screwtape.ai/mcp"}'

{
  "servers": {
    "screwtape-ai": {
      "type": "http",
      "url": "https://screwtape.ai/mcp"
    }
  }
}

{
  "mcpServers": {
    "screwtape-ai": {
      "serverUrl": "https://screwtape.ai/mcp"
    }
  }
}

codex mcp add screwtape-ai --url https://screwtape.ai/mcp

[mcp_servers.screwtape-ai]
url = "https://screwtape.ai/mcp"

gemini mcp add --transport http screwtape-ai https://screwtape.ai/mcp

{
  "mcpServers": {
    "screwtape-ai": {
      "type": "http",
      "url": "https://screwtape.ai/mcp"
    }
  }
}

Embed

Mostra Screwtape.ai in un README o sul tuo sito. Ogni embed rimanda a questa pagina, usa l’URL del server stesso e non imposta cookie. Come funzionano gli embed

Card, iframe e JSON sono in inglese. Aggiungi ?lang=it, fr, de o es al loro indirizzo per un’altra lingua.

Badge per il README Card per il sito iframe JSON Prompt per l’AI

Badge per il README

Markdown

[![Screwtape.ai on mcp.tc](https://mcp.tc/i/screwtape-ai/badge.svg)](https://mcp.tc/i/screwtape-ai)

HTML

<a href="https://mcp.tc/i/screwtape-ai"><img src="https://mcp.tc/i/screwtape-ai/badge.svg" alt="Screwtape.ai on mcp.tc" height="20"></a>

Segue la modalità chiara o scura di chi legge. Aggiungi ?theme=light o ?theme=dark per fissarla, oppure ?style=compact per mostrare il simbolo senza la scritta.

Card per il sito

HTML

<script src="https://mcp.tc/w/screwtape-ai.js" async></script>

La card compare dove si trova il tag. Aggiungi data-theme="dark" o data-size="compact" al tag per cambiarla. Il file contiene tutto ciò che serve, quindi non fa altre richieste e non imposta cookie.

iframe

HTML

<iframe src="https://mcp.tc/embed/screwtape-ai" title="Screwtape.ai on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Usalo nelle pagine che non consentono script. Aggiungi ?theme=light o ?theme=dark all’indirizzo per fissare i colori.

JSON

La scheda come dati per le tue pagine e i tuoi strumenti: nome, descrizione breve, URL del server, tool e i link «Add to». Qualsiasi sito può leggerla (CORS aperto).

https://mcp.tc/i/screwtape-ai.json

Cosa significa ogni campo

Prompt per l’AI

Incollalo in un assistente di programmazione con l’AI, come Claude Code o Cursor, e aggiungerà la card di Screwtape.ai al tuo sito.

Markdown

Aggiungi al mio sito la card di mcp.tc per Screwtape.ai, un server MCP. È un solo script statico: niente build, nessun pacchetto da installare, nessun cookie.

Metti questo tag dove deve comparire la card. La card appare subito prima del tag:

```html
<script src="https://mcp.tc/w/screwtape-ai.js" async></script>
```

Per mostrarla altrove, metti lì questo segnaposto e carica lo stesso script una volta sola, per esempio prima di `</body>`. Lascia il link al suo interno: lo vede chi non ha JavaScript.

```html
<div data-mcptc="screwtape-ai"><a href="https://mcp.tc/i/screwtape-ai">Screwtape.ai on mcp.tc</a></div>
```

Opzioni:
- `data-theme="light"` o `"dark"` sul tag o sul segnaposto fissa i colori. Senza l’attributo, la card segue la modalità chiara o scura di chi visita.
- `data-size="compact"` dà una card più piccola, senza la descrizione breve.
- La variabile CSS `--mcptc-max-width` sul segnaposto o su un elemento padre imposta la larghezza (predefinita `520px`).
- `?lang=` nell’URL dello script imposta la lingua della card: `en`, `it`, `fr`, `de` o `es`.

Se il sito ha una Content Security Policy, consenti `script-src https://mcp.tc` e `img-src data:` (l’icona è inline).

Per un README o altra documentazione in Markdown, usa invece il badge:

```markdown
[![Screwtape.ai on mcp.tc](https://mcp.tc/i/screwtape-ai/badge.svg)](https://mcp.tc/i/screwtape-ai)
```

Riferimento: https://mcp.tc/it/embed

Cronologia delle modifiche

Leggiamo l’elenco dei tool di questo server ogni 3 ore e registriamo cosa cambia. Ultima lettura: 15 nov 2026, 00:16 UTC.

1. 10 nov 2026, 05:48 UTC, Controllo automatico

   1 tool aggiunto. Istruzioni del server modificate.

   Nuove istruzioni del server

   Dettagli, 10 nov 2026, 05:48 UTC

   Aggiunti 1

   • payment_checkSola lettura

     Payment check: is this seller safe to pay, checked at the moment the agent pays. Compares the 402 price and payee with the seller's published listings when they can be fetched, screens the payee against a local denylist and the bundled OFAC SDN digital-currency address list, flags an over-price versus the intended amount, reuses the duplicate-payment check, and confirms the seller URL returns a valid 402. Returns allow, review or block with reasons and a signed receipt id. Fetches time out in about 2s and fail closed to review. $0.005 per call.

   Istruzioni del server

   Prima

   Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Call check_duplicate_invoice (Bearer key or x402 payment) before an agent pays an invoice or payment instruction: it returns duplicate.status (unique, duplicate, possible_duplicate, replay), runs the checks you pass (for example a sum check that line items add up to the total) and judges the invoice against your evidence, such as the purchase order. Pay only when next_step.action is pass; on escalate, do not pay. Every verdict carries a signed receipt as proof of why the money moved or did not. Use budget_ledger to reserve cumulative spend ($0.002); action_receipt signs an action record ($0.003). All five paid tools share 3 free calls per UTC day without a key plus 10/day with a free key. Anonymous: private daily IP namespace, 3/minute, global 2000/day. Free GET /v1/receipt/verify checks action receipts and /.well-known/screwtape-receipt-key publishes their key. Use judge on one draft answer before you return it (send evidence; it does not search the web). Use consensus when 2 to 16 answers to the same task agree and you are about to trust the majority. Use get_api_key only if no key is configured and you can compute SHA-256 in code. judge, check_duplicate_invoice and consensus cost one call each: a free key gives 10 per UTC day, or pay $0.005 USDC on Base or Solana with x402. After anonymous access is exhausted, an unpaid tools/call returns HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent and result._meta['x402/payment-required']. Retry with params._meta['x402/payment']. Settlement is echoed in result._meta['x402/payment-response']. Judged content is not stored unless retain is true or the key owner turned on opt-in data sharing (off by default; redacted, kept 90 days). A successful judge or consensus result includes an Ed25519 receipt when signing is configured. Public keys are at https://screwtape.ai/.well-known/screwtape-receipt-keys.json. PO…

   Dopo

   Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Call check_duplicate_invoice (Bearer key or x402 payment) before an agent pays an invoice or payment instruction: it returns duplicate.status (unique, duplicate, possible_duplicate, replay), runs the checks you pass (for example a sum check that line items add up to the total) and judges the invoice against your evidence, such as the purchase order. Pay only when next_step.action is pass; on escalate, do not pay. Every verdict carries a signed receipt as proof of why the money moved or did not. Use budget_ledger to reserve cumulative spend ($0.002); action_receipt signs an action record ($0.003). Use payment_check ($0.005) before paying a seller, to check the 402 payee and price. All six paid tools share 3 free calls per UTC day without a key plus 10/day with a free key. Anonymous: private daily IP namespace, 3/minute, global 2000/day. Free GET /v1/receipt/verify checks action receipts and /.well-known/screwtape-receipt-key publishes their key. Use judge on one draft answer before you return it (send evidence; it does not search the web). Use consensus when 2 to 16 answers to the same task agree and you are about to trust the majority. Use get_api_key only if no key is configured and you can compute SHA-256 in code. judge, check_duplicate_invoice and consensus cost one call each: a free key gives 10 per UTC day, or pay $0.005 USDC on Base or Solana with x402. After anonymous access is exhausted, an unpaid tools/call returns HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent and result._meta['x402/payment-required']. Retry with params._meta['x402/payment']. Settlement is echoed in result._meta['x402/payment-response']. Judged content is not stored unless retain is true or the key owner turned on opt-in data sharing (off by default; redacted, kept 90 days). A successful judge or consensus result includes an Ed25519 receipt when signing is configured.…

2. 9 nov 2026, 14:50 UTC, Controllo automatico

   Nuova versione 1.3.0 (prima 1.2.2). Dichiarata dal server.

3. 9 nov 2026, 14:50 UTC, Controllo automatico

   1 tool modificato.

   Dettagli, 9 nov 2026, 14:50 UTC

   Modificati 1

   • action_receiptdescrizione, schema di input e schema di output
     Prima

     Action Receipts: Ed25519-signed, hash-chained attestation of an agent-reported action and status; not evidence the action happened or a legal compliance certification. Per caller and agent chain; concurrent appends serialize with compare-and-set. Raw action/reference are hashed, not stored. event_id per agent is the authoritative idempotency key; a custom HTTP key cannot override it. Same event_id/body returns the same receipt; changed body conflicts. GET /v1/receipt/verify?id=<receipt_id> is free and returns the receipt to anyone who knows its unguessable ID. Or pass receipt=<JSON> to verify a portable receipt. Keep IDs private if your agent IDs/status are sensitive. Records persist until the API key is deleted; keyless records have no automatic expiry. $0.003 per call; shared 3 free calls per UTC day without a key (daily private IP namespace), plus 10/day with a free key. Anonymous scopes rotate daily; use a key for a persistent ledger/chain. Send the same Bearer key plus a payment…

     Dopo

     Action Receipts: Ed25519-signed, hash-chained attestation of an agent-reported action and status; not evidence the action happened or a legal compliance certification. Per caller and agent chain; concurrent appends serialize with compare-and-set. Raw action/reference are hashed, not stored. event_id per agent is the authoritative idempotency key; a custom HTTP key cannot override it. Same event_id/body returns the same receipt; changed body conflicts. Optional children (1-64 receipt UUIDs) closes a run: the signed children_root digests ordered child receipt_hash values so any added, dropped or swapped step fails verification. GET /v1/receipt/verify?id=<receipt_id> is free and returns the receipt to anyone who knows its unguessable ID; children_root_valid is set when children are present. A receipt proves the record is unchanged since issued, not that a payment was correct or an outside action happened. Or pass receipt=<JSON> to verify a portable receipt. Keep IDs private if your agent…

     • Nuovi parametri: children

4. 7 nov 2026, 14:47 UTC, Controllo automatico

   Nuova versione 1.2.2 (prima 1.2.0). Dichiarata dal server.

5. 7 nov 2026, 02:45 UTC, Controllo automatico

   2 tool aggiunti e 3 tool modificati. Istruzioni del server modificate.

   Nuove istruzioni del server

   Dettagli, 7 nov 2026, 02:45 UTC

   Aggiunti 2

   • action_receiptScrive

     Action Receipts: Ed25519-signed, hash-chained attestation of an agent-reported action and status; not evidence the action happened or a legal compliance certification. Per caller and agent chain; concurrent appends serialize with compare-and-set. Raw action/reference are hashed, not stored. event_id per agent is the authoritative idempotency key; a custom HTTP key cannot override it. Same event_id/body returns the same receipt; changed body conflicts. GET /v1/receipt/verify?id=<receipt_id> is free and returns the receipt to anyone who knows its unguessable ID. Or pass receipt=<JSON> to verify a portable receipt. Keep IDs private if your agent IDs/status are sensitive. Records persist until the API key is deleted; keyless records have no automatic expiry. $0.003 per call; shared 3 free calls per UTC day without a key (daily private IP namespace), plus 10/day with a free key. Anonymous scopes rotate daily; use a key for a persistent ledger/chain. Send the same Bearer key plus a payment…

   • budget_ledgerScrive

     Budget Ledger: atomically reserves reported USD spend across a run and its sub-agents. Returns allow/warn/block, remaining budget, retry storms and spend velocity. Call judge first, then reserve immediately before spending; honor block. This is cooperative accounting, not payment enforcement. Root cap and parent are immutable. Children inherit the root cap (send the same cap). event_id is the authoritative idempotency key; a custom HTTP key cannot override it. New event_id per attempted action; same event_id and body replays without reserving twice. No refunds or cap resets. Warn reservations count as spend. Limits: USD, six decimals, cap at most 1000000. Three matching actions in 60 seconds allowed; fourth blocked. Velocity warning at ten attempts/minute or more than 25% of cap/minute; 80% usage warns. Use action to distinguish operations at a merchant. Stored: IDs, keyed fingerprints and amounts, not raw action/merchant. Records persist until the API key is deleted; keyless records…

   Modificati 3

   • check_duplicate_invoicedescrizione
     Prima

     Spend gate for invoices: decides whether an agent may pay this invoice, with a signed receipt as proof. Same as judge with one duplicate check: it compares this invoice with the invoices this caller recorded earlier and also judges it. Call it before an agent pays or approves an invoice or payment instruction. Inputs: the judge inputs (task, agent_output as the invoice JSON, evidence, criteria, checks, mode, tags) plus duplicate {vendor_path, invoice_id_path, amount_path, currency_path?, date_path?, payee_account_path?, accept_payee_change?, window_days?, store?, retain_days?}. Returns the judge result plus duplicate.status (unique, duplicate, possible_duplicate, replay or not_checked). On duplicate or possible_duplicate, next_step.action is escalate: do not pay. Fingerprints are kept per caller; only keyed HMAC fingerprints are stored, and only when store is true. Cost: 1 call, the same as judge. Needs Authorization: Bearer <key>, or a per-call payment in params._meta with no key (re…

     Dopo

     Spend gate for invoices: decides whether an agent may pay this invoice, with a signed receipt as proof. Same as judge with one duplicate check: it compares this invoice with the invoices this caller recorded earlier and also judges it. Call it before an agent pays or approves an invoice or payment instruction. Inputs: the judge inputs (task, agent_output as the invoice JSON, evidence, criteria, checks, mode, tags) plus duplicate {vendor_path, invoice_id_path, amount_path, currency_path?, date_path?, payee_account_path?, accept_payee_change?, window_days?, store?, retain_days?}. Returns the judge result plus duplicate.status (unique, duplicate, possible_duplicate, replay or not_checked). On duplicate or possible_duplicate, next_step.action is escalate: do not pay. Fingerprints are kept per caller; only keyed HMAC fingerprints are stored, and only when store is true. Cost: 1 call, the same as judge. First 3 calls per UTC day need no key (daily private IP namespace). Then use Authorizati…

   • consensusdescrizione

     Il testo mostrato qui è uguale prima e dopo: la modifica è oltre i primi 1.000 caratteri o in caratteri che non si vedono.

   • judgedescrizione
     Prima

     A pass/fail/retry verdict on ONE agent output, from a service outside your agent, used as the go/no-go before an agent spends money or acts on that output. Call it before you pay on, return, store or act on a draft answer, especially when you have the evidence the answer should be based on. Do NOT call it to look up facts (it does no web search and only checks against the evidence you pass), to compare several agents' answers (use consensus), or for offline evaluation over a dataset. Inputs: task, agent_output, evidence, criteria, retain, and optional agent_id and version tags. Returns: verdict, score, reasons, engine, next_step, request_id, retention, the tags when sent, and receipt when signing is configured. On pass, use the output. On retry, revise using reasons and call again, at most 2 or 3 times. On fail, stop. Optional checks run first; on failure you get next_step.hint saying what to fix. Branch on next_step.action (pass, retry or escalate). Cost: 1 call. Needs Authorization:…

     Dopo

     A pass/fail/retry verdict on ONE agent output, from a service outside your agent, used as the go/no-go before an agent spends money or acts on that output. Call it before you pay on, return, store or act on a draft answer, especially when you have the evidence the answer should be based on. Do NOT call it to look up facts (it does no web search and only checks against the evidence you pass), to compare several agents' answers (use consensus), or for offline evaluation over a dataset. Inputs: task, agent_output, evidence, criteria, retain, and optional agent_id and version tags. Returns: verdict, score, reasons, engine, next_step, request_id, retention, the tags when sent, and receipt when signing is configured. On pass, use the output. On retry, revise using reasons and call again, at most 2 or 3 times. On fail, stop. Optional checks run first; on failure you get next_step.hint saying what to fix. Branch on next_step.action (pass, retry or escalate). Cost: 1 call. First 3 calls per UT…

   Istruzioni del server

   Prima

   Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Call check_duplicate_invoice (Bearer key or x402 payment) before an agent pays an invoice or payment instruction: it returns duplicate.status (unique, duplicate, possible_duplicate, replay), runs the checks you pass (for example a sum check that line items add up to the total) and judges the invoice against your evidence, such as the purchase order. Pay only when next_step.action is pass; on escalate, do not pay. Every verdict carries a signed receipt as proof of why the money moved or did not. Use judge on one draft answer before you return it (send evidence; it does not search the web). Use consensus when 2 to 16 answers to the same task agree and you are about to trust the majority. Use get_api_key only if no key is configured and you can compute SHA-256 in code. judge, check_duplicate_invoice and consensus cost one call each: a free key gives 10 per UTC day, or pay $0.005 USDC on Base or Solana with x402. An unpaid tools/call returns HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent and result._meta['x402/payment-required']. Retry with params._meta['x402/payment']. Settlement is echoed in result._meta['x402/payment-response']. Judged content is not stored unless retain is true or the key owner turned on opt-in data sharing (off by default; redacted, kept 90 days). A successful judge or consensus result includes an Ed25519 receipt when signing is configured. Public keys are at https://screwtape.ai/.well-known/screwtape-receipt-keys.json. POST /v1/receipts/verify checks a receipt. publish_receipt publishes one receipt you own. It needs the Bearer key and does not accept x402.

   Dopo

   Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Call check_duplicate_invoice (Bearer key or x402 payment) before an agent pays an invoice or payment instruction: it returns duplicate.status (unique, duplicate, possible_duplicate, replay), runs the checks you pass (for example a sum check that line items add up to the total) and judges the invoice against your evidence, such as the purchase order. Pay only when next_step.action is pass; on escalate, do not pay. Every verdict carries a signed receipt as proof of why the money moved or did not. Use budget_ledger to reserve cumulative spend ($0.002); action_receipt signs an action record ($0.003). All five paid tools share 3 free calls per UTC day without a key plus 10/day with a free key. Anonymous: private daily IP namespace, 3/minute, global 2000/day. Free GET /v1/receipt/verify checks action receipts and /.well-known/screwtape-receipt-key publishes their key. Use judge on one draft answer before you return it (send evidence; it does not search the web). Use consensus when 2 to 16 answers to the same task agree and you are about to trust the majority. Use get_api_key only if no key is configured and you can compute SHA-256 in code. judge, check_duplicate_invoice and consensus cost one call each: a free key gives 10 per UTC day, or pay $0.005 USDC on Base or Solana with x402. After anonymous access is exhausted, an unpaid tools/call returns HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent and result._meta['x402/payment-required']. Retry with params._meta['x402/payment']. Settlement is echoed in result._meta['x402/payment-response']. Judged content is not stored unless retain is true or the key owner turned on opt-in data sharing (off by default; redacted, kept 90 days). A successful judge or consensus result includes an Ed25519 receipt when signing is configured. Public keys are at https://screwtape.ai/.well-known/screwtape-receipt-keys.json. PO…

6. 6 nov 2026, 20:45 UTC, Controllo automatico

   Istruzioni del server modificate.

   Nuove istruzioni del server

   Dettagli, 6 nov 2026, 20:45 UTC

   Istruzioni del server

   Prima

   Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Call check_duplicate_invoice (Bearer key or x402 payment) before an agent pays an invoice or payment instruction: it returns duplicate.status (unique, duplicate, possible_duplicate, replay), runs the checks you pass (for example a sum check that line items add up to the total) and judges the invoice against your evidence, such as the purchase order. Pay only when next_step.action is pass; on escalate, do not pay. Every verdict carries a signed receipt as proof of why the money moved or did not. Use judge on one draft answer before you return it (send evidence; it does not search the web). Use consensus when 2 to 16 answers to the same task agree and you are about to trust the majority. Use get_api_key only if no key is configured and you can compute SHA-256 in code. judge, check_duplicate_invoice and consensus cost one call each: a free key gives 10 per UTC day, or pay $0.005 USDC on Base or Solana with x402. An unpaid tools/call returns HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent. Retry with params._meta['x402/payment']. Settlement is echoed in result._meta['x402/payment-response']. Judged content is not stored unless retain is true or the key owner turned on opt-in data sharing (off by default; redacted, kept 90 days). A successful judge or consensus result includes an Ed25519 receipt when signing is configured. Public keys are at https://screwtape.ai/.well-known/screwtape-receipt-keys.json. POST /v1/receipts/verify checks a receipt. publish_receipt publishes one receipt you own. It needs the Bearer key and does not accept x402.

   Dopo

   Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Call check_duplicate_invoice (Bearer key or x402 payment) before an agent pays an invoice or payment instruction: it returns duplicate.status (unique, duplicate, possible_duplicate, replay), runs the checks you pass (for example a sum check that line items add up to the total) and judges the invoice against your evidence, such as the purchase order. Pay only when next_step.action is pass; on escalate, do not pay. Every verdict carries a signed receipt as proof of why the money moved or did not. Use judge on one draft answer before you return it (send evidence; it does not search the web). Use consensus when 2 to 16 answers to the same task agree and you are about to trust the majority. Use get_api_key only if no key is configured and you can compute SHA-256 in code. judge, check_duplicate_invoice and consensus cost one call each: a free key gives 10 per UTC day, or pay $0.005 USDC on Base or Solana with x402. An unpaid tools/call returns HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent and result._meta['x402/payment-required']. Retry with params._meta['x402/payment']. Settlement is echoed in result._meta['x402/payment-response']. Judged content is not stored unless retain is true or the key owner turned on opt-in data sharing (off by default; redacted, kept 90 days). A successful judge or consensus result includes an Ed25519 receipt when signing is configured. Public keys are at https://screwtape.ai/.well-known/screwtape-receipt-keys.json. POST /v1/receipts/verify checks a receipt. publish_receipt publishes one receipt you own. It needs the Bearer key and does not accept x402.

7. 5 nov 2026, 23:46 UTC, Controllo automatico

   1 tool aggiunto, 1 tool rimosso e 4 tool modificati. Istruzioni del server modificate.

   Nuove istruzioni del server

   Dettagli, 5 nov 2026, 23:46 UTC

   Aggiunti 1

   • try_checkSola lettura

     See what a spend check returns before you have a key. Runs ONE sample check on a fixed demo invoice: a duplicate match against an invoice paid earlier, required fields, and a sum check that the line items add up to the total. Call it once to learn the response shape. Do NOT call it on your own invoices (it ignores them; use check_duplicate_invoice) or in a loop: it is limited to 5 calls per hour per IP and per MCP session. Inputs: scenario (optional: duplicate, the default, clean, or bad_total). Returns: demo, scenario, invoice, earlier_invoice, duplicate.status (unique or duplicate), checks, next_step.action (pass, retry or escalate), note, next_action and request_id. No receipt and nothing is stored. Cost: free. Needs no key.

   Rimossi 1

   • buy_pack

     Retired. No prepaid pack is sold to agents any more (Starter and Builder were retired), so this tool always returns the error pack_retired with how a person buys the Sandbox Evaluation Pack by card. It does not move funds and needs no key. Kept so existing clients get a clear answer. To pay per call without a key, call judge or consensus and handle the x402 payment requirements.

   Modificati 4

   • check_duplicate_invoicedescrizione, schema di input e schema di output
     Prima

     Duplicate invoice check before an agent pays. Same as judge with one duplicate check: it compares this invoice with the invoices this API key recorded earlier and also judges it. Call it before an agent pays or approves an invoice or payment instruction. Inputs: the judge inputs (task, agent_output as the invoice JSON, evidence, criteria, checks, mode, tags) plus duplicate {vendor_path, invoice_id_path, amount_path, currency_path?, date_path?, window_days?, store?, retain_days?}. Returns the judge result plus duplicate.status (unique, duplicate, possible_duplicate, replay or not_checked). On duplicate or possible_duplicate, next_step.action is escalate: do not pay. Needs Authorization: Bearer, because fingerprints are kept per key; only keyed HMAC fingerprints are stored, and only when store is true. Cost: 1 call, the same price as judge. Without a key or payment, tools/call is HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent; an x402 payment without a…

     Dopo

     Spend gate for invoices: decides whether an agent may pay this invoice, with a signed receipt as proof. Same as judge with one duplicate check: it compares this invoice with the invoices this caller recorded earlier and also judges it. Call it before an agent pays or approves an invoice or payment instruction. Inputs: the judge inputs (task, agent_output as the invoice JSON, evidence, criteria, checks, mode, tags) plus duplicate {vendor_path, invoice_id_path, amount_path, currency_path?, date_path?, payee_account_path?, accept_payee_change?, window_days?, store?, retain_days?}. Returns the judge result plus duplicate.status (unique, duplicate, possible_duplicate, replay or not_checked). On duplicate or possible_duplicate, next_step.action is escalate: do not pay. Fingerprints are kept per caller; only keyed HMAC fingerprints are stored, and only when store is true. Cost: 1 call, the same as judge. Needs Authorization: Bearer <key>, or a per-call payment in params._meta with no key (re…

     • Descrizione di checks
       Prima

       Optional. The worker runs each check. A failed check forces verdict fail. Types: url_contains, json_schema, equals, regex, numeric, onchain, required_fields, types, format, sum, duplicate. duplicate…

       Dopo

       Optional. The worker runs each check. A failed check forces verdict fail. Types include url_contains, json_schema, equals, regex, numeric, required_fields, types, format, sum and duplicate. duplicate…

     • Descrizione di duplicate
       Prima

       The duplicate check: dot paths into agent_output for vendor, invoice id and amount, plus optional currency_path, date_path, window_days, store and retain_days. store true records this invoice's keyed…

       Dopo

       The duplicate check: dot paths into agent_output for vendor, invoice id and amount, plus optional currency_path, date_path, payee_account_path, accept_payee_change, window_days, store and retain_days…

   • consensusdescrizione, schema di input e schema di output
     Prima

     False-consensus check for 2 to 16 answers to the same task. It scores how the answers agree and flags agreement that looks copied or too thin to trust. Screwtape is not tied to the agent framework or the model that wrote the answers. Call it when several agents, samples or tools answered the same question and you are about to accept the majority. Do NOT call it with a single answer (use judge), with answers to different tasks, or as proof that an answer is correct: high agreement is not evidence. Inputs: task, answers (2 to 16 objects {agent_id?: string, output: string}), optional evidence (a string or an array of strings, used when scoring), retain, and optional call-level agent_id and version tags. The call-level agent_id is not the per-answer agent_id. Returns: consensus_answer, agreement_score, false_consensus_risk (low, medium or high), reasons, clusters, engine, request_id, retention, the tags when sent, and receipt when signing is configured. In that receipt, verdict is false_c…

     Dopo

     False-consensus check for 2 to 16 answers to the same task, so a group of agents does not approve a spend just because they copied each other. It scores how the answers agree and flags agreement that looks copied or too thin to trust. Screwtape is not tied to the agent framework or the model that wrote the answers. Call it when several agents, samples or tools answered the same question and you are about to accept the majority. Do NOT call it with a single answer (use judge), with answers to different tasks, or as proof that an answer is correct: high agreement is not evidence. Inputs: task, answers (2 to 16 objects {agent_id?: string, output: string}), optional evidence (a string or an array of strings, used when scoring), retain, and optional call-level agent_id and version tags. The call-level agent_id is not the per-answer agent_id. Returns: consensus_answer, agreement_score, false_consensus_risk (low, medium or high), reasons, clusters, engine, request_id, retention, the tags whe…

     • Descrizione di answers
       Prima

       2 to 16 answers. Each is {agent_id (optional, string), output (string)}. Use one entry per independent agent or sample.

       Dopo

       2 to 16 answers. Each is {agent_id (optional, string), output (string)}. Use one entry per agent or sample.

   • judgedescrizione, schema di input e schema di output
     Prima

     An independent pass/fail/retry verdict on ONE agent output. Call it before you return, store or act on a draft answer, especially when you have the evidence the answer should be based on. Do NOT call it to look up facts (it does no web search and only checks against the evidence you pass), to compare several agents' answers (use consensus), or for offline evaluation over a dataset. Inputs: task, agent_output, evidence, criteria, retain, and optional agent_id and version tags. Returns: verdict, score, reasons, engine, next_step, request_id, retention, the tags when sent, and receipt when signing is configured. On pass, use the output. On retry, revise using reasons and call again, at most 2 or 3 times. On fail, stop. Optional checks run first; on failure you get next_step.hint saying what to fix. Branch on next_step.action (pass, retry or escalate). Cost: 1 call. A free key covers 10 calls per UTC day; without a key, pay $0.005 USDC on Base or Solana per call with x402. Without a key o…

     Dopo

     A pass/fail/retry verdict on ONE agent output, from a service outside your agent, used as the go/no-go before an agent spends money or acts on that output. Call it before you pay on, return, store or act on a draft answer, especially when you have the evidence the answer should be based on. Do NOT call it to look up facts (it does no web search and only checks against the evidence you pass), to compare several agents' answers (use consensus), or for offline evaluation over a dataset. Inputs: task, agent_output, evidence, criteria, retain, and optional agent_id and version tags. Returns: verdict, score, reasons, engine, next_step, request_id, retention, the tags when sent, and receipt when signing is configured. On pass, use the output. On retry, revise using reasons and call again, at most 2 or 3 times. On fail, stop. Optional checks run first; on failure you get next_step.hint saying what to fix. Branch on next_step.action (pass, retry or escalate). Cost: 1 call. Needs Authorization:…

     • Descrizione di checks
       Prima

       Optional. The worker runs each check. A failed check forces verdict fail. Types: url_contains, json_schema, equals, regex, numeric, onchain, required_fields, types, format, sum, duplicate. duplicate…

       Dopo

       Optional. The worker runs each check. A failed check forces verdict fail. Types include url_contains, json_schema, equals, regex, numeric, required_fields, types, format, sum and duplicate. duplicate…

   • publish_receiptdescrizione
     Prima

     Publish a signed receipt you own so a public page and a Screwtape Verified badge can link to that one verdict. Call it when you want to show that a specific output received a specific verdict. Do NOT call it to certify an agent in general: the page says this output received this verdict at this time, and it is not a general safety certification of the agent. Nothing is public until this call. Inputs: receipt_id (required), include_content (optional boolean, default false; true stores and shows the task and agent output only if that call was retained), label (optional, at most 80 characters), unpublish (optional boolean; true removes the public page). Returns public_url, badge_svg_url, embed_html, and embed_markdown. Requires the API key that owns the receipt. It does not accept x402 payment. Cost: free.

     Dopo

     Publish a signed receipt you own so a public page and a Screwtape Verified badge can link to that one verdict. Call it when you want to show that a specific output received a specific verdict. Do NOT call it to certify an agent in general: the page says this output received this verdict at this time, and it is not a general safety certification of the agent. Nothing is public until this call. Inputs: receipt_id (required), include_content (optional boolean, default false; true stores and shows the task and agent output only if that call was retained), label (optional, at most 80 characters), unpublish (optional boolean; true removes the public page). Returns public_url, badge_svg_url, embed_html, and embed_markdown. Requires the API key that owns the receipt. Cost: free.

   Istruzioni del server

   Prima

   Verify before the agent pays: a separate check on agent work before a payment goes out (invoices, duplicate invoices, reconciliation), with signed receipts. Use check_duplicate_invoice with a Bearer key before an agent pays an invoice; it returns duplicate.status and costs one call like judge. Screwtape also gives false-consensus checks and pass/fail/retry verdicts for any agent output. Use judge on one draft answer before you return it (send evidence; it does not search the web). Use consensus when 2 to 16 answers to the same task agree and you are about to trust the majority. Use get_api_key only if no key is configured and you can compute SHA-256 in code. judge and consensus cost one call each: a free key gives 100 per UTC day, or pay $0.005 USDC on Base or Solana with x402. An unpaid tools/call returns HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent. Retry with params._meta['x402/payment']. Settlement is echoed in result._meta['x402/payment-response']. Judged content is not stored unless retain is true or the key owner turned on opt-in data sharing (off by default; redacted, kept 90 days). A successful judge or consensus result includes an Ed25519 receipt when signing is configured. Public keys are at https://screwtape.ai/.well-known/screwtape-receipt-keys.json. POST /v1/receipts/verify checks a receipt. publish_receipt publishes one receipt you own. It needs the Bearer key and does not accept x402. Not the arXiv paper named Screwtape.

   Dopo

   Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Call check_duplicate_invoice (Bearer key or x402 payment) before an agent pays an invoice or payment instruction: it returns duplicate.status (unique, duplicate, possible_duplicate, replay), runs the checks you pass (for example a sum check that line items add up to the total) and judges the invoice against your evidence, such as the purchase order. Pay only when next_step.action is pass; on escalate, do not pay. Every verdict carries a signed receipt as proof of why the money moved or did not. Use judge on one draft answer before you return it (send evidence; it does not search the web). Use consensus when 2 to 16 answers to the same task agree and you are about to trust the majority. Use get_api_key only if no key is configured and you can compute SHA-256 in code. judge, check_duplicate_invoice and consensus cost one call each: a free key gives 10 per UTC day, or pay $0.005 USDC on Base or Solana with x402. An unpaid tools/call returns HTTP 200 with isError true and the x402 PaymentRequirements in structuredContent. Retry with params._meta['x402/payment']. Settlement is echoed in result._meta['x402/payment-response']. Judged content is not stored unless retain is true or the key owner turned on opt-in data sharing (off by default; redacted, kept 90 days). A successful judge or consensus result includes an Ed25519 receipt when signing is configured. Public keys are at https://screwtape.ai/.well-known/screwtape-receipt-keys.json. POST /v1/receipts/verify checks a receipt. publish_receipt publishes one receipt you own. It needs the Bearer key and does not accept x402.

8. 27 ott 2026, 11:59 UTC, Controllo automatico

   1 tool modificato.

   Dettagli, 27 ott 2026, 11:59 UTC

   Modificati 1

   • buy_packdescrizione
     Prima

     Retired. No prepaid pack is sold to agents any more (Starter and Builder were retired), so this tool always returns the error pack_retired with how a person buys the Evaluation Pack by card. It does not move funds and needs no key. Kept so existing clients get a clear answer. To pay per call without a key, call judge or consensus and handle the x402 payment requirements.

     Dopo

     Retired. No prepaid pack is sold to agents any more (Starter and Builder were retired), so this tool always returns the error pack_retired with how a person buys the Sandbox Evaluation Pack by card. It does not move funds and needs no key. Kept so existing clients get a clear answer. To pay per call without a key, call judge or consensus and handle the x402 payment requirements.

9. 27 ott 2026, 05:41 UTC, Controllo automatico

   1 tool modificato.

   Dettagli, 27 ott 2026, 05:41 UTC

   Modificati 1

   • buy_packdescrizione, titolo, schema di input e indicazioni
     Prima

     Return the x402 payment requirements for the Starter prepaid pack ($40, 10000 calls), plus how to pay with USDC on Base or Solana. pack is starter. This call does not move funds and does not require a key or a payment. POST /v1/packs/{pack}/buy with PAYMENT-SIGNATURE to pay. Pay with PayPal at POST /v1/packs/checkout.

     Dopo

     Retired. No prepaid pack is sold to agents any more (Starter and Builder were retired), so this tool always returns the error pack_retired with how a person buys the Evaluation Pack by card. It does not move funds and needs no key. Kept so existing clients get a clear answer. To pay per call without a key, call judge or consensus and handle the x402 payment requirements.

     titolo

     Prima

     Buy a prepaid pack with USDC

     Dopo

     Retired: prepaid packs are no longer sold to agents

     • Non più obbligatori: pack
     • Descrizione di pack
       Prima

       starter ($40, 10000 calls).

       Dopo

       Any former pack id. Ignored: every pack answers pack_retired.

10. 26 ott 2026, 05:44 UTC, Controllo automatico

    4 tool modificati.

    Dettagli, 26 ott 2026, 05:44 UTC

    Modificati 4

    • buy_packdescrizione e schema di input
      Prima

      Return the x402 payment requirements for a Starter ($40, 10000 calls) or Builder ($175, 50000 calls) prepaid pack, plus how to pay with USDC on Base or Solana. pack is starter or builder. This call does not move funds and does not require a key or a payment. POST /v1/packs/{pack}/buy with PAYMENT-SIGNATURE to pay. Pay with PayPal at POST /v1/packs/checkout.

      Dopo

      Return the x402 payment requirements for the Starter prepaid pack ($40, 10000 calls), plus how to pay with USDC on Base or Solana. pack is starter. This call does not move funds and does not require a key or a payment. POST /v1/packs/{pack}/buy with PAYMENT-SIGNATURE to pay. Pay with PayPal at POST /v1/packs/checkout.

      • Descrizione di pack
        Prima

        starter ($40, 10000 calls) or builder ($175, 50000 calls).

        Dopo

        starter ($40, 10000 calls).

    • consensusdescrizione

      Il testo mostrato qui è uguale prima e dopo: la modifica è oltre i primi 1.000 caratteri o in caratteri che non si vedono.

    • get_api_keydescrizione
      Prima

      Create a free Screwtape.ai API key (100 calls per UTC day) with no human approval. Call it only when no Screwtape key is configured and you can compute SHA-256 with a code tool, because the proof of work must be computed exactly, not guessed. Do NOT call it when a key already exists, to get more quota (it is limited to 5 keys per IP per hour and per UTC day), or without a valid pow_nonce. A missing nonce returns an error that describes the challenge. Inputs: pow_nonce (required string matching ^[A-Za-z0-9_-]{8,64}$; SHA-256 of the UTF-8 string screwtape-signup-v1:<current UTC YYYY-MM-DD>:<nonce> must start with 12 zero bits, which is 3 hex zeros), email (optional), name (optional, at most 80 characters). Returns: api_key (shown once; store it securely and send it as Authorization: Bearer), key metadata and request_id. Only the key's SHA-256 hash is stored. Cost: free. Needs no key and no payment.

      Dopo

      Create a free Screwtape.ai API key (10 calls per UTC day) with no human approval. Call it only when no Screwtape key is configured and you can compute SHA-256 with a code tool, because the proof of work must be computed exactly, not guessed. Do NOT call it when a key already exists, to get more quota (it is limited to 5 keys per IP per hour and per UTC day), or without a valid pow_nonce. A missing nonce returns an error that describes the challenge. Inputs: pow_nonce (required string matching ^[A-Za-z0-9_-]{8,64}$; SHA-256 of the UTF-8 string screwtape-signup-v1:<current UTC YYYY-MM-DD>:<nonce> must start with 12 zero bits, which is 3 hex zeros), email (optional), name (optional, at most 80 characters). Returns: api_key (shown once; store it securely and send it as Authorization: Bearer), key metadata and request_id. Only the key's SHA-256 hash is stored. Cost: free. Needs no key and no payment.

    • judgedescrizione
      Prima

      An independent pass/fail/retry verdict on ONE agent output. Call it before you return, store or act on a draft answer, especially when you have the evidence the answer should be based on. Do NOT call it to look up facts (it does no web search and only checks against the evidence you pass), to compare several agents' answers (use consensus), or for offline evaluation over a dataset. Inputs: task, agent_output, evidence, criteria, retain, and optional agent_id and version tags. Returns: verdict, score, reasons, engine, next_step, request_id, retention, the tags when sent, and receipt when signing is configured. On pass, use the output. On retry, revise using reasons and call again, at most 2 or 3 times. On fail, stop. Optional checks run first; on failure you get next_step.hint saying what to fix. Branch on next_step.action (pass, retry or escalate). Cost: 1 call. A free key covers 100 calls per UTC day; without a key, pay $0.005 USDC on Base or Solana per call with x402. Without a key…

      Dopo

      An independent pass/fail/retry verdict on ONE agent output. Call it before you return, store or act on a draft answer, especially when you have the evidence the answer should be based on. Do NOT call it to look up facts (it does no web search and only checks against the evidence you pass), to compare several agents' answers (use consensus), or for offline evaluation over a dataset. Inputs: task, agent_output, evidence, criteria, retain, and optional agent_id and version tags. Returns: verdict, score, reasons, engine, next_step, request_id, retention, the tags when sent, and receipt when signing is configured. On pass, use the output. On retry, revise using reasons and call again, at most 2 or 3 times. On fail, stop. Optional checks run first; on failure you get next_step.hint saying what to fix. Branch on next_step.action (pass, retry or escalate). Cost: 1 call. A free key covers 10 calls per UTC day; without a key, pay $0.005 USDC on Base or Solana per call with x402. Without a key o…

11. 24 ott 2026, 19:45 UTC, Controllo automatico

    Nuova versione 1.2.0 (prima 1.1.0). Dichiarata dal server.

12. 24 ott 2026, 19:45 UTC, Controllo automatico

    3 tool modificati.

    Dettagli, 24 ott 2026, 19:45 UTC

    Modificati 3

    check_duplicate_invoice consensus judge

    Le 10 voci più recenti mostrano ogni dettaglio; le più vecchie mostrano solo i nomi.

13. 24 ott 2026, 07:28 UTC, Controllo automatico

    Inizio del tracciamento: 6 tool.

Domande frequenti