Curated bundles of Tinplate micro-APIs for AI agent security, LLM data pipelines, and European compliance.
Model Context Protocol (MCP) tool descriptions are injected directly into your LLM's system prompt. Tinplate gives you deterministic static linting for mcp.json manifests plus runtime argument, shell, SQL, and code guards.
5 Edge APIs → AI Agent SSRF Protection APIAutonomous agents that browse URLs, fetch webhooks, or read Markdown can be tricked into probing 169.254.169.254, 127.0.0.1, or internal VPC services. Validate and normalize untrusted URLs before your agent ever opens a socket.
5 Edge APIs → Prompt Injection, PII Redaction & JSON RepairProtect both sides of your LLM call: strip PII and API secrets before prompts leave your VPC, block Unicode/Base64 prompt injections, and deterministically heal broken JSON before it crashes your downstream parser.
6 Edge APIs → EU VAT, VIES, IBAN & Peppol UBL ValidatorBuilt for European B2B SaaS, fintechs, and invoicing pipelines. Verify VAT formats and live EU VIES registration, validate IBAN/BIC checksums, lint Peppol BIS 3.0 UBL XML invoices, and screen counterparties against EU/UN/OFAC sanctions.
6 Edge APIs →