Screwtape.ai

Über den Server

Screwtape.ai ist eine unabhängige Prüfinstanz für die Ausgaben von KI-Agenten. Er beurteilt einen einzelnen Antwortentwurf anhand vorgelegter Belege, bewertet die Übereinstimmung von 2 bis 16 Antworten, um falschen Konsens zu erkennen, und prüft Rechnungen auf Duplikate, bevor ein Agent sie bezahlt. Erfolgreiche Ergebnisse können einen mit Ed25519 signierten Beleg enthalten, und ein Beleg lässt sich als Verifizierungs-Badge veröffentlichen.

Er läuft als gehosteter Streamable-HTTP-Endpunkt unter https://screwtape.ai/mcp. Aufrufe nutzen einen Bearer-API-Schlüssel (ein kostenloser Schlüssel erlaubt 100 Aufrufe pro UTC-Tag) oder eine Zahlung pro Aufruf von 0,005 $ USDC auf Base oder Solana über x402. Beurteilte Inhalte werden nicht gespeichert, außer retain ist auf true gesetzt.

Was du damit machen kannst

• Urteil (bestanden, nicht bestanden oder erneut versuchen) zu einer Agentenausgabe anhand von Belegen abrufen
• Rechnung auf Duplikate prüfen, bevor ein Agent sie bezahlt
• Falschen Konsens bei 2 bis 16 Antworten bewerten
• Kostenlosen API-Schlüssel über eine Proof-of-Work-Registrierung erstellen
• Zahlungsanforderungen für vorausbezahlte Aufrufpakete abrufen
• Signierten Beleg als öffentliches Verifizierungs-Badge veröffentlichen

Tools 9

• budget_ledgerSchreibt

  Budget Ledger

• action_receiptSchreibt

  Action Receipts

• payment_checkLiest nur

  Payment check

• judgeLiest nur

  Gibt ein Urteil (bestanden, nicht bestanden oder erneut versuchen) zu einer Agentenausgabe zurück, geprüft anhand vorgelegter Belege.

• check_duplicate_invoiceSchreibt

  Beurteilt eine Rechnung und vergleicht sie mit früher erfassten Rechnungen, um den Duplikatstatus zu melden.

• consensusLiest nur

  Bewertet die Übereinstimmung von 2 bis 16 Antworten und markiert kopierten oder dünnen Konsens.

• get_api_keySchreibt

  Erstellt einen kostenlosen API-Schlüssel (100 Aufrufe pro UTC-Tag) mit einem SHA-256-Proof-of-Work.

• publish_receiptSchreibt

  Veröffentlicht einen eigenen signierten Beleg als öffentliche Screwtape-Verified-Badge-Seite.

• try_checkLiest nur

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

Am 15. Nov. 2026 vom laufenden Server gelesen. „Liest nur“, „Schreibt“ und „Kann löschen“ sind Hinweise, die der Server selbst angibt; dein Client entscheidet, ob er vor dem Ausführen eines Tools nachfragt.

Beispiel-Prompts

• Prüfe diese Rechnung auf Duplikate, bevor du sie bezahlst.

• Beurteile meinen Antwortentwurf anhand dieser Belege und sag mir, ob er besteht.

• Führe eine Konsensprüfung für diese fünf Agentenantworten durch.

• Veröffentliche den Beleg des letzten Urteils als Badge.

Einrichtung

Jeder Client verbindet sich mit screwtape.ai. Wähl deinen; die Seite merkt sich deine Wahl.

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"
    }
  }
}

Einbinden

Zeig Screwtape.ai in einem README oder auf deiner Website. Jede Einbindung verlinkt auf diese Seite, nutzt die eigene URL des Servers und setzt keine Cookies. So funktionieren Einbindungen

Karte, iframe und JSON sind auf Englisch. Häng ?lang=it, fr, de oder es an ihre Adresse an, um eine andere Sprache zu bekommen.

README-Badge Website-Karte iframe JSON KI-Prompt

README-Badge

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>

Es folgt dem hellen oder dunklen Modus der Lesenden. Hänge ?theme=light oder ?theme=dark an, um ihn festzulegen, oder ?style=compact, um das Zeichen ohne Schriftzug zu zeigen.

Website-Karte

HTML

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

Die Karte erscheint dort, wo das Tag steht. Füge dem Tag data-theme="dark" oder data-size="compact" hinzu, um sie zu ändern. Die Datei enthält alles, was sie braucht, stellt also keine weiteren Anfragen und setzt keine Cookies.

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>

Nutze es auf Seiten, die keine Skripte erlauben. Hänge ?theme=light oder ?theme=dark an die Adresse an, um die Farben festzulegen.

JSON

Der Eintrag als Daten für deine eigenen Seiten und Tools: Name, Kurzbeschreibung, die eigene URL des Servers, Tools und die „Add to“-Links. Jede Website kann ihn lesen (CORS ist offen).

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

Was jedes Feld bedeutet

KI-Prompt

Füg ihn in einen KI-Coding-Assistenten wie Claude Code oder Cursor ein, und er baut die Karte von Screwtape.ai in deine Website ein.

Markdown

Füge meiner Website die mcp.tc-Karte für den MCP-Server Screwtape.ai hinzu. Es ist ein einziges statisches Skript: kein Build-Schritt, kein Paket zu installieren, keine Cookies.

Setz dieses Tag dorthin, wo die Karte erscheinen soll. Die Karte erscheint direkt davor:

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

Um sie woanders zu zeigen, setz dort diesen Platzhalter ein und lade dasselbe Skript nur einmal, zum Beispiel vor `</body>`. Lass den Link darin stehen: Besucher ohne JavaScript sehen ihn.

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

Optionen:
- `data-theme="light"` oder `"dark"` am Tag oder Platzhalter legt die Farben fest. Ohne das Attribut folgt die Karte dem hellen oder dunklen Modus der Besucher.
- `data-size="compact"` ergibt eine kleinere Karte ohne Kurzbeschreibung.
- Die CSS-Variable `--mcptc-max-width` am Platzhalter oder einem Elternelement legt die Breite fest (Standard `520px`).
- `?lang=` in der Skript-URL legt die Sprache der Karte fest: `en`, `it`, `fr`, `de` oder `es`.

Wenn die Website eine Content Security Policy hat, erlaube `script-src https://mcp.tc` und `img-src data:` (das Icon ist eingebettet).

Für ein README oder andere Markdown-Dokumentation nimm stattdessen das Badge:

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

Referenz: https://mcp.tc/de/embed

Änderungsverlauf

Wir lesen die Tool-Liste dieses Servers alle 3 Stunden und halten fest, was sich ändert. Zuletzt gelesen: 15. Nov. 2026, 00:16 UTC.

1. 10. Nov. 2026, 05:48 UTC, Automatische Prüfung

   1 Tool hinzugefügt. Server-Anweisungen geändert.

   Neue Server-Anweisungen

   Details, 10. Nov. 2026, 05:48 UTC

   Hinzugefügt 1

   • payment_checkLiest nur

     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.

   Server-Anweisungen

   Vorher

   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…

   Nachher

   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, Automatische Prüfung

   Neue Version 1.3.0 (vorher 1.2.2). Vom Server gemeldet.

3. 9. Nov. 2026, 14:50 UTC, Automatische Prüfung

   1 Tool geändert.

   Details, 9. Nov. 2026, 14:50 UTC

   Geändert 1

   • action_receiptBeschreibung, Eingabeschema und Ausgabeschema
     Vorher

     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…

     Nachher

     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…

     • Neue Parameter: children

4. 7. Nov. 2026, 14:47 UTC, Automatische Prüfung

   Neue Version 1.2.2 (vorher 1.2.0). Vom Server gemeldet.

5. 7. Nov. 2026, 02:45 UTC, Automatische Prüfung

   2 Tools hinzugefügt und 3 Tools geändert. Server-Anweisungen geändert.

   Neue Server-Anweisungen

   Details, 7. Nov. 2026, 02:45 UTC

   Hinzugefügt 2

   • action_receiptSchreibt

     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_ledgerSchreibt

     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…

   Geändert 3

   • check_duplicate_invoiceBeschreibung
     Vorher

     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…

     Nachher

     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…

   • consensusBeschreibung

     Der hier gezeigte Text ist vorher und nachher gleich: Die Änderung liegt hinter den ersten 1.000 Zeichen oder in Zeichen, die man nicht sieht.

   • judgeBeschreibung
     Vorher

     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:…

     Nachher

     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…

   Server-Anweisungen

   Vorher

   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.

   Nachher

   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, Automatische Prüfung

   Server-Anweisungen geändert.

   Neue Server-Anweisungen

   Details, 6. Nov. 2026, 20:45 UTC

   Server-Anweisungen

   Vorher

   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.

   Nachher

   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, Automatische Prüfung

   1 Tool hinzugefügt, 1 Tool entfernt und 4 Tools geändert. Server-Anweisungen geändert.

   Neue Server-Anweisungen

   Details, 5. Nov. 2026, 23:46 UTC

   Hinzugefügt 1

   • try_checkLiest nur

     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.

   Entfernt 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.

   Geändert 4

   • check_duplicate_invoiceBeschreibung, Eingabeschema und Ausgabeschema
     Vorher

     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…

     Nachher

     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…

     • Beschreibung von checks
       Vorher

       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…

       Nachher

       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…

     • Beschreibung von duplicate
       Vorher

       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…

       Nachher

       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…

   • consensusBeschreibung, Eingabeschema und Ausgabeschema
     Vorher

     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…

     Nachher

     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…

     • Beschreibung von answers
       Vorher

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

       Nachher

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

   • judgeBeschreibung, Eingabeschema und Ausgabeschema
     Vorher

     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…

     Nachher

     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:…

     • Beschreibung von checks
       Vorher

       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…

       Nachher

       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_receiptBeschreibung
     Vorher

     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.

     Nachher

     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.

   Server-Anweisungen

   Vorher

   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.

   Nachher

   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. Okt. 2026, 11:59 UTC, Automatische Prüfung

   1 Tool geändert.

   Details, 27. Okt. 2026, 11:59 UTC

   Geändert 1

   • buy_packBeschreibung
     Vorher

     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.

     Nachher

     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. Okt. 2026, 05:41 UTC, Automatische Prüfung

   1 Tool geändert.

   Details, 27. Okt. 2026, 05:41 UTC

   Geändert 1

   • buy_packBeschreibung, Titel, Eingabeschema und Hinweise
     Vorher

     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.

     Nachher

     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.

     Titel

     Vorher

     Buy a prepaid pack with USDC

     Nachher

     Retired: prepaid packs are no longer sold to agents

     • Nicht mehr Pflicht: pack
     • Beschreibung von pack
       Vorher

       starter ($40, 10000 calls).

       Nachher

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

10. 26. Okt. 2026, 05:44 UTC, Automatische Prüfung

    4 Tools geändert.

    Details, 26. Okt. 2026, 05:44 UTC

    Geändert 4

    • buy_packBeschreibung und Eingabeschema
      Vorher

      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.

      Nachher

      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.

      • Beschreibung von pack
        Vorher

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

        Nachher

        starter ($40, 10000 calls).

    • consensusBeschreibung

      Der hier gezeigte Text ist vorher und nachher gleich: Die Änderung liegt hinter den ersten 1.000 Zeichen oder in Zeichen, die man nicht sieht.

    • get_api_keyBeschreibung
      Vorher

      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.

      Nachher

      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.

    • judgeBeschreibung
      Vorher

      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…

      Nachher

      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. Okt. 2026, 19:45 UTC, Automatische Prüfung

    Neue Version 1.2.0 (vorher 1.1.0). Vom Server gemeldet.

12. 24. Okt. 2026, 19:45 UTC, Automatische Prüfung

    3 Tools geändert.

    Details, 24. Okt. 2026, 19:45 UTC

    Geändert 3

    check_duplicate_invoice consensus judge

    Die neuesten 10 Änderungen zeigen alle Details, ältere nur die Namen.

13. 24. Okt. 2026, 07:28 UTC, Automatische Prüfung

    Beginn der Beobachtung: 6 Tools.

Häufige Fragen