Screwtape.ai

Descripción

Screwtape.ai es una comprobación independiente de la salida de agentes de IA. Juzga un único borrador de respuesta frente a las evidencias aportadas, puntúa la coincidencia entre 2 y 16 respuestas para detectar falsos consensos y comprueba si hay facturas duplicadas antes de que un agente las pague. Los resultados correctos pueden incluir un recibo firmado con Ed25519, y un recibo puede publicarse como insignia de verificación.

Funciona como un endpoint Streamable HTTP alojado en https://screwtape.ai/mcp. Las llamadas usan una clave de API Bearer (una clave gratuita permite 100 llamadas por día UTC) o un pago por llamada de 0,005 $ en USDC sobre Base o Solana mediante x402. El contenido juzgado no se almacena a menos que retain se establezca en true.

Qué puedes hacer

• Obtener un veredicto de pass, fail o retry sobre una salida de agente frente a evidencias
• Comprobar si una factura está duplicada antes de que un agente la pague
• Puntuar de 2 a 16 respuestas para detectar falso consenso
• Crear una clave de API gratuita mediante un registro con prueba de trabajo
• Obtener los requisitos de pago de paquetes de llamadas prepagados
• Publicar un recibo firmado como insignia verificada pública

Herramientas 9

• budget_ledgerEscritura

  Budget Ledger

• action_receiptEscritura

  Action Receipts

• payment_checkSolo lectura

  Payment check

• judgeSolo lectura

  Devolver un veredicto de pass, fail o retry sobre una salida de agente, comprobada frente a las evidencias aportadas.

• check_duplicate_invoiceEscritura

  Juzgar una factura y compararla con facturas registradas anteriormente para informar de su estado de duplicado.

• consensusSolo lectura

  Puntuar la coincidencia entre 2 y 16 respuestas y señalar consensos copiados o débiles.

• get_api_keyEscritura

  Crear una clave de API gratuita (100 llamadas por día UTC) mediante una prueba de trabajo SHA-256.

• publish_receiptEscritura

  Publicar un recibo firmado propio como página pública de insignia Screwtape Verified.

• try_checkSolo lectura

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

Leídas del servidor en funcionamiento el 15 nov 2026. Solo lectura, Escritura y Puede borrar son indicaciones que declara el servidor; tu cliente decide si te pregunta antes de ejecutar una herramienta.

Prompts de ejemplo

• Comprueba si esta factura está duplicada antes de pagarla.

• Juzga mi borrador de respuesta frente a esta evidencia y dime si pasa.

• Ejecuta una comprobación de consenso sobre estas cinco respuestas de agentes.

• Publica el recibo del último veredicto como insignia.

Configuración

Todos los clientes se conectan a screwtape.ai. Elige el tuyo; la página recuerda tu elección.

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"
    }
  }
}

Insertar

Muestra Screwtape.ai en un README o en tu web. Cada inserción enlaza a esta página, usa la URL propia del servidor y no instala cookies. Cómo funcionan las inserciones

La tarjeta, el iframe y el JSON están en inglés. Añade ?lang=it, fr, de o es a su dirección para otro idioma.

Insignia para README Tarjeta para web iframe JSON Prompt para la IA

Insignia para 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>

Sigue el modo claro u oscuro de quien lee. Añade ?theme=light o ?theme=dark para fijarlo, o ?style=compact para mostrar el símbolo sin la palabra.

Tarjeta para web

HTML

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

La tarjeta aparece donde esté la etiqueta. Añade data-theme="dark" o data-size="compact" a la etiqueta para cambiarla. El archivo contiene todo lo que necesita, así que no hace otras solicitudes ni instala 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>

Úsalo en páginas que no permiten scripts. Añade ?theme=light o ?theme=dark a la dirección para fijar los colores.

JSON

La ficha como datos para tus propias páginas y herramientas: nombre, descripción corta, la URL propia del servidor, herramientas y los enlaces «Add to». Cualquier web puede leerla (CORS abierto).

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

Qué significa cada campo

Prompt para la IA

Pégalo en un asistente de programación con IA, como Claude Code o Cursor, y añadirá la tarjeta de Screwtape.ai a tu web.

Markdown

Añade a mi web la tarjeta de mcp.tc de Screwtape.ai, un servidor MCP. Es un solo script estático: sin paso de build, sin paquetes que instalar, sin cookies.

Pon esta etiqueta donde deba aparecer la tarjeta. La tarjeta se muestra justo antes de ella:

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

Para mostrarla en otro sitio, pon allí este marcador y carga el mismo script una sola vez, por ejemplo antes de `</body>`. Deja el enlace dentro: lo ven los visitantes sin JavaScript.

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

Opciones:
- `data-theme="light"` o `"dark"` en la etiqueta o el marcador fija los colores. Sin él, la tarjeta sigue el modo claro u oscuro del visitante.
- `data-size="compact"` da una tarjeta más pequeña, sin el eslogan.
- La variable CSS `--mcptc-max-width` en el marcador o en un elemento padre fija el ancho (por defecto `520px`).
- `?lang=` en la URL del script fija el idioma de la tarjeta: `en`, `it`, `fr`, `de` o `es`.

Si el sitio tiene una Content Security Policy, permite `script-src https://mcp.tc` e `img-src data:` (el icono va incrustado).

Para un README u otra documentación en Markdown, usa la insignia:

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

Referencia: https://mcp.tc/es/embed

Historial de cambios

Leemos la lista de herramientas de este servidor cada 3 horas y registramos lo que cambia. Última lectura: 15 nov 2026, 00:16 UTC.

1. 10 nov 2026, 05:48 UTC, Comprobación automática

   1 herramienta añadida. Instrucciones del servidor cambiadas.

   Nuevas instrucciones del servidor

   Detalles, 10 nov 2026, 05:48 UTC

   Añadidas 1

   • payment_checkSolo lectura

     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.

   Instrucciones del servidor

   Antes

   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…

   Después

   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, Comprobación automática

   Nueva versión 1.3.0 (antes 1.2.2). Declarada por el servidor.

3. 9 nov 2026, 14:50 UTC, Comprobación automática

   1 herramienta cambiada.

   Detalles, 9 nov 2026, 14:50 UTC

   Cambiadas 1

   • action_receiptdescripción, esquema de entrada y esquema de salida
     Antes

     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…

     Después

     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…

     • Parámetros nuevos: children

4. 7 nov 2026, 14:47 UTC, Comprobación automática

   Nueva versión 1.2.2 (antes 1.2.0). Declarada por el servidor.

5. 7 nov 2026, 02:45 UTC, Comprobación automática

   2 herramientas añadidas y 3 herramientas cambiadas. Instrucciones del servidor cambiadas.

   Nuevas instrucciones del servidor

   Detalles, 7 nov 2026, 02:45 UTC

   Añadidas 2

   • action_receiptEscritura

     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_ledgerEscritura

     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…

   Cambiadas 3

   • check_duplicate_invoicedescripción
     Antes

     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…

     Después

     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…

   • consensusdescripción

     El texto que se muestra aquí es igual antes y después: el cambio está más allá de los primeros 1000 caracteres o en caracteres que no se ven.

   • judgedescripción
     Antes

     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:…

     Después

     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…

   Instrucciones del servidor

   Antes

   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.

   Después

   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, Comprobación automática

   Instrucciones del servidor cambiadas.

   Nuevas instrucciones del servidor

   Detalles, 6 nov 2026, 20:45 UTC

   Instrucciones del servidor

   Antes

   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.

   Después

   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, Comprobación automática

   1 herramienta añadida, 1 herramienta eliminada y 4 herramientas cambiadas. Instrucciones del servidor cambiadas.

   Nuevas instrucciones del servidor

   Detalles, 5 nov 2026, 23:46 UTC

   Añadidas 1

   • try_checkSolo lectura

     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.

   Eliminadas 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.

   Cambiadas 4

   • check_duplicate_invoicedescripción, esquema de entrada y esquema de salida
     Antes

     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…

     Después

     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…

     • Descripción de checks
       Antes

       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…

       Después

       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…

     • Descripción de duplicate
       Antes

       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…

       Después

       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…

   • consensusdescripción, esquema de entrada y esquema de salida
     Antes

     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…

     Después

     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…

     • Descripción de answers
       Antes

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

       Después

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

   • judgedescripción, esquema de entrada y esquema de salida
     Antes

     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…

     Después

     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:…

     • Descripción de checks
       Antes

       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…

       Después

       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_receiptdescripción
     Antes

     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.

     Después

     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.

   Instrucciones del servidor

   Antes

   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.

   Después

   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 oct 2026, 11:59 UTC, Comprobación automática

   1 herramienta cambiada.

   Detalles, 27 oct 2026, 11:59 UTC

   Cambiadas 1

   • buy_packdescripción
     Antes

     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.

     Después

     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 oct 2026, 05:41 UTC, Comprobación automática

   1 herramienta cambiada.

   Detalles, 27 oct 2026, 05:41 UTC

   Cambiadas 1

   • buy_packdescripción, título, esquema de entrada y indicaciones
     Antes

     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.

     Después

     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.

     título

     Antes

     Buy a prepaid pack with USDC

     Después

     Retired: prepaid packs are no longer sold to agents

     • Ya no obligatorios: pack
     • Descripción de pack
       Antes

       starter ($40, 10000 calls).

       Después

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

10. 26 oct 2026, 05:44 UTC, Comprobación automática

    4 herramientas cambiadas.

    Detalles, 26 oct 2026, 05:44 UTC

    Cambiadas 4

    • buy_packdescripción y esquema de entrada
      Antes

      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.

      Después

      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.

      • Descripción de pack
        Antes

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

        Después

        starter ($40, 10000 calls).

    • consensusdescripción

      El texto que se muestra aquí es igual antes y después: el cambio está más allá de los primeros 1000 caracteres o en caracteres que no se ven.

    • get_api_keydescripción
      Antes

      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.

      Después

      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.

    • judgedescripción
      Antes

      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…

      Después

      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 oct 2026, 19:45 UTC, Comprobación automática

    Nueva versión 1.2.0 (antes 1.1.0). Declarada por el servidor.

12. 24 oct 2026, 19:45 UTC, Comprobación automática

    3 herramientas cambiadas.

    Detalles, 24 oct 2026, 19:45 UTC

    Cambiadas 3

    check_duplicate_invoice consensus judge

    Las 10 entradas más recientes muestran todos los detalles; las anteriores, solo los nombres.

13. 24 oct 2026, 07:28 UTC, Comprobación automática

    Inicio del seguimiento: 6 herramientas.

Preguntas frecuentes