Loading ToolBench
Connect your MONEI account to manage payments, generate payment links, and view transaction history through AI assistants (Claude, ChatGPT) via OAuth 2.0
MONEI MCP Server demonstrates solid tool design with complete schemas, clear descriptions, and proper parameter typing. All 6 tools have descriptions (avg 150 chars), input schemas with typed parameters, and enum constraints where appropriate. Tool names follow verb_noun convention (generate_payment_link, get_payment, list_payments). However, output schemas are not documented, LLMs cannot see what fields to expect from responses. Error handling is basic (generic 'Error: {message}' text). Missing are: per-parameter descriptions for some fields, output schema documentation, and recovery guidance in error messages. Audit logging and rate limiting are implemented server-side, which is good security practice.
Create a payment link that can be shared with a customer. Returns a URL the customer can use to complete the payment. Supports cards, Bizum, and other MONEI-enabled payment methods.
Retrieve your MONEI merchant account information including business name, supported payment methods, and account configuration.
Retrieve the full details and current status of a payment by its ID. Returns amount, status, payment method, customer info, and timestamps.
Retrieve the full details and current status of a subscription by its ID. Returns amount, interval, status, and billing period information.
List and search payments with optional filters. Returns a paginated list of transactions. Useful for checking recent sales, finding specific orders, or reviewing payment history.
Output schemas not documented. LLMs cannot see what fields get_payment, list_payments, get_subscription, list_subscriptions, or get_account_info return. This forces agents to guess field names for downstream operations and risks broken tool chains.
Error responses are generic text ('Error: {message}') with no recovery guidance. When a payment lookup fails, the LLM receives no hint about what to try next (e.g., 'Payment not found. Try list_payments() to find the correct ID').
list_payments and list_subscriptions accept limit and offset but do not document total count or next_cursor in responses. Without pagination metadata, agents cannot reliably iterate through large result sets.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 69 | <=2025-11-25 | v2 |
List subscriptions with optional filters. Returns active, paused, and past subscriptions.
generate_payment_link accepts optional expireAt (Unix timestamp) but description does not clarify format or provide guidance on reasonable values. LLMs may pass invalid timestamps.
No tool supports refunds, cancellations, or subscription modifications. The system prompt warns agents these are restricted, but no alternative path is offered (e.g., 'contact support' tool or documentation link).