MCP servers for AI agents
9 production pre-action validators. Agents call these before taking consequential actions — verifying counterparties, VAT numbers, tenders, HS codes, URLs, data payloads, model routing decisions, quantum POC viability, and document integrity. HTTP transport. No install required.
Bizfile MCP — Counterparty Validator
Call before approving a payment, onboarding a supplier, or signing a contract. Returns KYC confidence HIGH/MEDIUM/LOW, AI risk score 0-100, company officers, and sanctions screen across 328 lists.
| tool | tier | what it returns |
|---|---|---|
| validate_counterparty | free · 20/month | Registry lookup, active status, KYC confidence, AI risk score, officers list |
| validate_counterparty_lite | free · 20/month | Fast registry-only check, no AI scoring — company status, registration number, address. Low token cost, sub-second response. |
| screen_counterparty | paid | Screens company + all officers against 328 sanctions lists. BLOCK/EDD/PROCEED verdict. |
VAT Validator MCP
Call before issuing an invoice, processing a cross-border payment, or storing a VAT number. Validates EU, UK, and AU VAT numbers in real time against official government registries.
| tool | tier | what it returns |
|---|---|---|
| validate_vat | free · 20/month | EU VIES validation — valid flag, company name, address |
| validate_uk_vat | free · 20/month | HMRC real-time validation — valid flag, business name |
| get_vat_rates | free · 20/month | Current VAT rates for any country |
| batch_validate | paid | Validate up to 50 VAT numbers in one call |
| analyse_vat_risk | free · 20/month | AI fraud risk scoring — CLEAR/REVIEW/BLOCK verdict, risk score 0-100, fraud signals, agent_action field |
| compare_invoice_details | free · 20/month | Cross-checks invoice VAT details against live registry — MATCH/MISMATCH verdict, field-level detail, agent_action |
Tender MCP
Call when an agent needs to find relevant government contracts or evaluate a specific tender opportunity. Searches UK, EU, and US government procurement databases simultaneously.
| tool | tier | what it returns |
|---|---|---|
| search_tenders | free · 10/month | Keyword search across UK Contracts Finder, EU TED, SAM.gov — title, value, deadline, link |
| get_tender_intelligence | paid | AI analysis of a specific tender — fit score, win factors, risk flags, recommended approach |
URL Safety Validator MCP
Call before your agent fetches, visits, or forwards any URL from an untrusted source — emails, scraped pages, documents, API responses. Returns a single SAFE/SUSPICIOUS/DANGEROUS verdict with AI trust score.
| tool | tier | what it returns |
|---|---|---|
| check_url | free · 10/month | SAFE/SUSPICIOUS/DANGEROUS verdict, AI trust score 0-100, threat categories, SSL status, domain age, redirect chain flag. Cross-checks Google Web Risk + Google Safe Browsing + AI analysis. |
Data Compliance Classifier MCP
Call before storing, transmitting, or processing any data payload. Classifies PII, detects applicable regulations (GDPR, HIPAA, CCPA, PCI-DSS), checks credential breach exposure, and returns a SAFE_TO_PROCESS/ESCALATE/DO_NOT_STORE verdict.
| tool | tier | what it returns |
|---|---|---|
| validate_data_safety | free · 20/month | PII classification, jurisdiction detection, breach check, compliance verdict |
| get_safety_report | paid | Batch up to 50 payloads + audit report + AbuseIPDB threat intelligence |
Local Model Suitability MCP
Call before routing a task to an API model. Determines whether the task can be handled by a local Ollama model — reducing cost and latency for simple tasks while reserving API calls for tasks that need them.
| tool | tier | what it returns |
|---|---|---|
| check_local_viability | free · 20/month | LOCAL/API/CONFIDENTIAL verdict, recommended Ollama model, estimated cost saving, confidence score |
HS Code Classifier MCP
Call before completing any customs declaration, shipping manifest, or duty calculation. Classifies product descriptions to official HS codes using government tariff schedules (USITC, Singapore Customs, CBSA, AU Border Force, WCO) with AI-assisted reasoning.
| tool | tier | what it returns |
|---|---|---|
| hs_classify_product | free · 10/month | HS code, WCO 6-digit parent, official source, tariff version, AI classification reasoning, agent_action field |
| hs_validate_code | paid | Validates supplier-provided HS code — VALID/INVALID/MISMATCH/OUTDATED verdict, product match score, mismatch reason, correct code suggestion |
Quantum Suitability Validator MCP
Call before your agent escalates a quantum computing initiative to a human committee, allocates POC budget, or routes to a quantum specialist. Refusal-first AI triage engine screens against expert decision rules — QUBO failure patterns, penalty dominance, hype language detection.
| tool | tier | what it returns |
|---|---|---|
| quantum_assess_problem | free · 5/month | 7-verdict system (RECOMMENDED_NOW through NOT_QUANTUM_AMENABLE), suitability score, confidence score, problem class, dominant blockers, hype flags, agent_action field |
| quantum_readiness_report | paid | Full auditable report: QUBO/Ising/variational formulation guidance, hardware family fit (D-Wave/IBM/IonQ), error budget assessment, classical baseline benchmark, validation plan |
Document Integrity Validator MCP
Checks any document against named international standards before your agent acts on it. Free 10 calls/month.
| tool | tier | what it returns |
|---|---|---|
| check_document | free · 10/month | Checks a single document against its international standard — PROCEED/VERIFY_MANUALLY/HOLD/REFER_TO_HUMAN verdict, flags, confidence score |
| check_document_package | paid | Checks 2-20 related documents and cross-checks for consistency conflicts — weights, party names, reference numbers, dates, commodity descriptions, port references |