Run a full compliance check on an IBAN: validates the IBAN, enriches with bank data, then screens against sanctions lists, checks SEPA reachability, verifies VoP participation, and computes a composite risk score. When to use: assessing compliance risk of a payment recipient for AML/KYC workflow...
Single-target operation
Part of the Ibanforge MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call compliance_check to retrieve information from Ibanforge without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though compliance_check only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
compliance_check:
rules:
- action: allowSee the full Ibanforge policy for all 5 tools.
Agents calling read-class tools like compliance_check have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Run a full compliance check on an IBAN: validates the IBAN, enriches with bank data, then screens against sanctions lists, checks SEPA reachability, verifies VoP participation, and computes a composite risk score. When to use: assessing compliance risk of a payment recipient for AML/KYC workflows, verifying an IBAN is not associated with a sanctioned country or bank, checking SEPA Instant and Verification of Payee participation, or producing a structured risk assessment before approving a payment. When NOT to use: for simple IBAN format validation without compliance data, use validate_iban (4x cheaper). For BIC-only lookups, use lookup_bic. Behavior: this tool is read-only with no side effects. It performs IBAN validation and enrichment (same as validate_iban), then queries a local compliance database for sanctions (OFAC/EU/UN lists), FATF grey/black list status, SEPA scheme participation (SCT, SDD, SCT_INST), and VoP participant status. Computes a composite risk score from 0 (lowest risk) to 100 (highest risk) based on 21 weighted risk flags. Response time is under 50ms. Returns a single JSON object. If compliance data is unavailable for a country/BIC, returns a fallback risk_level of 'elevated' with a flag 'compliance_data_unavailable'. Risk score weights: sanctioned country (+50), sanctioned bank (+50), FATF black list (+30), FATF grey list (+20), high-risk country (+20), elevated-risk country (+10), payment institution issuer (+15), EMI issuer (+10), no SEPA Instant (+5), no VoP (+5), test BIC (+30). Risk levels: low (0-19), medium (20-39), elevated (40-59), high (60-79), critical (80-100). Returns: { valid, country, bban, bic, sepa, issuer, risk_indicators, compliance: { sanctions: { country_sanctioned, bank_sanctioned, matched_lists, fatf_status }, reachability: { sepa_instant, sct, sdd }, vop: { participant, status }, risk_score, risk_level, flags } } Example: input 'DE89370400440532013000' → { valid: true, compliance: { sanctions: { country_sanctioned: false, fatf_status: 'member' }, risk_score: 5, risk_level: 'low', flags: [] } } Cost: $0.02 USDC per call via x402 micropayment on Base L2.. It is categorised as a Read tool in the Ibanforge MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for compliance_check. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Ibanforge MCP server.
compliance_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the compliance_check rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for compliance_check. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
compliance_check is provided by the Ibanforge MCP server (ibanforge). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept