Categories › Business & Finance › Payments & billing
Spend guardrails for AI agents: check payments, track budgets, catch duplicates, sign receipts.
Remote server: your requests and data go to screwtape.ai. Claude Code: claude mcp add --transport http screwtape-ai https://screwtape.ai/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
budget_ledger — Budget Ledger: atomically reserves reported USD spend across a run and its sub-agents. Returns allow/warn/block, remaining budget, retry stoaction_receipt — Action Receipts: Ed25519-signed, hash-chained attestation of an agent-reported action and status; not evidence the action happened or a legapayment_check — 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 publishejudge — 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 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 checonsensus — 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 otheget_api_key — 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 cpublish_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 showtry_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 paNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.