Screwtape.ai

active

Headline: POST /v1/payment-check answers is this seller safe to pay, for $0.005 a call (allow, review or block, with a signed receipt). Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Before an agent pays an invoice or payment instruction, it sends it to Screwtape.ai first. POST /v1/duplicate (MCP tool checkduplicateinvoice) checks it against the invoices…

AIBaseSolanax402 v2exactscrewtape.ai ↗︎

Settled via Coinbase.

Transactions · 30d
27
Volume · 30d
$0.139
Unique buyers · 30d
6
Uptime · 30d
100.0%
Latency p50
120ms
Reported calls · 30d
22

Endpoints (20 live)

  • POST /v1/consensus — False-consensus check before agents act or spend on a shared answer: agreement score and risk for 2 to 16 agent answers, with a signed receipt. (0.005 USDC on Base)
  • POST /v1/duplicate — Duplicate invoice check before an agent pays. Same price as /v1/judge ($0.005 USDC per call), no API key needed. Fingerprints are kept per paying wallet. (0.005 USDC on Base)
  • POST /v1/judge — Spend gate for AI agents: pass, fail or retry on an invoice, payment instruction or any agent output, checked against your evidence and checks (such as line items summing to the total), with an Ed25519-signed receipt. (0.005 USDC on Base)
  • POST /v1/receipt — Action Receipts: signed hash-chained action attestation. Optional children (prior receipt ids) close a whole run. $0.003 USDC per call. (0.003 USDC on Base)
  • POST /v1/budget — Budget Ledger: cumulative run and sub-agent spend, cap enforcement, retry storms and velocity. $0.002 USDC per call. (0.002 USDC on Base)
  • POST /v1/packages/metered_spend_clearance/buy — Metered spend clearance: $29 USDC on Base for 5000 clearances, valid 30 days. Prepaid, not a subscription. (29 USDC on Base)
  • GET /v1/pre-pay-bundle (0.03 USDC on Base)
  • POST /v1/pre-pay-bundle — Pre-pay bundle: one call before an agent pays a seller. Seller 402 and listing check, payee screen (denylist and OFAC), over-price and duplicate check, then records an approved payment so a repeat is blocked later, with a signed receipt. allow, review or block. $0.03 USDC per call. (0.03 USDC on Base)
  • POST /v1/trust-score — Seller trust score: is this paying agent risky? Cross-seller velocity, failed/refused payments, disputes, new vs established. Score, allow/review/block and reasons. $0.02 USDC per call. (0.02 USDC on Base)
  • GET /v1/trust-score (0.005 USDC on Base)
  • POST /v1/payment-check — Payment check: is this seller safe to pay? Compares the 402 price and payee with published listings, screens the payee, flags over-price and duplicates, and checks that the seller URL returns a valid 402. allow, review or block, with a signed receipt. $0.005 USDC per call. (0.005 USDC on Base)
  • GET /v1/budget (0.002 USDC on Solana)
  • GET /v1/payment-check (0.005 USDC on Solana)
  • GET /v1/receipt (0.003 USDC on Solana)
  • HEAD /v1/duplicate — Duplicate invoice check before an agent pays. Same price as /v1/judge ($0.005 USDC per call), no API key needed. Fingerprints are kept per paying wallet. (0.005 USDC on Base)
  • GET /v1/duplicate — Duplicate invoice check before an agent pays. Same price as /v1/judge ($0.005 USDC per call), no API key needed. Fingerprints are kept per paying wallet. (0.005 USDC on Base)
  • HEAD /v1/judge — Spend gate for AI agents: pass, fail or retry on an invoice, payment instruction or any agent output, checked against your evidence and checks (such as line items summing to the total), with an Ed25519-signed receipt. (0.005 USDC on Base)
  • GET /v1/consensus — False-consensus check before agents act or spend on a shared answer: agreement score and risk for 2 to 16 agent answers, with a signed receipt. (0.005 USDC on Base)
  • HEAD /v1/consensus — False-consensus check before agents act or spend on a shared answer: agreement score and risk for 2 to 16 agent answers, with a signed receipt. (0.005 USDC on Base)
  • GET /v1/judge — Spend gate for AI agents: pass, fail or retry on an invoice, payment instruction or any agent output, checked against your evidence and checks (such as line items summing to the total), with an Ed25519-signed receipt. (0.005 USDC on Base)

MCP tools (12)

Screwtape.ai https://screwtape.ai/mcp

  • action_receipt — 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
  • budget_ledger — 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 h
  • buy_package — Buy a prepaid Screwtape.ai agent package instantly. package must be metered_spend_clearance ($29 for 5,000 Payment Guard clearances, 30 days) or agent_fleet_compliance ($19 for 1,000 trust-score calls, 30 days). Optional api_key tops up that key; otherwise a new key is returned once. An unpaid call returns payment requirements (in MCP: isError true and structuredContent set to the requirements). Retry the same tool call with payment in params._meta. No email and no human step. Prepaid, not a subscription: buy again to renew.
  • check_duplicate_invoice — 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 Authorizatio
  • consensus — 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 when
  • get_api_key — Create a free Screwtape.ai API key (10 calls per UTC day) with no human approval and no code: call it with an empty object {} or just a name. Call it only when no Screwtape key is configured. Do NOT call it when a key already exists, or to get more quota. Keys without a proof of work are limited to 2 per network and 300 per service per UTC day; add pow_nonce (optional; 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; nonce matches ^[A-Za-z0-9_-]{8,64}$) only if you can run code and hit that limit. Other inputs: 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. You do not need a key to start: the first 3 calls per UTC day work with no key and no payment. Cost: free.
  • judge — 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 UTC
  • payment_check — Call this before paying any unknown seller or URL. 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. Try it free first (3 calls a day without a key), then pay per call.
  • payment_guard_authorize — Payment Guard: enforce your own spend rules before an agent pays. Set rules once per API key (or an account default): max_per_call_usd, daily_budget_usd, period_budget_usd + period_hours, allowed_sellers, allowed_domains, max_calls_per_minute, max_calls_per_hour. Then send each payment intent to POST /v1/payment-guard/authorize: allow returns a short-lived Ed25519-signed clearance (not a payment signature) and reserves the amount against your budgets atomically; block returns HTTP 403 with reasons and nothing is reserved. POST /v1/payment-guard/proxy does the same check and, on allow, forwards your client-signed PAYMENT-SIGNATURE (or X-PAYMENT) to the seller once per event_id. Non-custodial: Screwtape.ai never holds funds and never accepts private keys, seeds or mnemonics. Requires a Bearer API key. authorize and proxy use one shared free-tier or prepaid call each ($0.005 equivalent); rules endpoints are free. Same event_id + body replays the decision without billing again. Over MCP, s
  • publish_receipt — 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.
  • trust_score — Seller trust score: check whether a paying agent looks abusive or risky before you accept payment. Scores velocity, failed or refused payments, dispute-like patterns, and new versus established history across the Screwtape.ai seller network. Returns a 0–1 trust score, allow/review/block, risk and reasons. Subject values are hashed with a global network HMAC; reporter contributions are weighted by how the reporter paid (per-call payment > prepaid > free) and capped per reporter. window and observations are mutually exclusive. Raw IPs, payer addresses and keys are never stored. $0.02 per call (shared free tier; no monthly plan).
  • try_check — 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 30 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, paid_upgrade (what a $0.005 paid call on your own invoices adds, and a pay snippet) and request_id. No receipt and nothing is stored. Cost: free. Needs no key.

First seen · last seen · last active