Taiwan Payments & E-Invoice (ECPay 綠界 / NewebPay 藍新)
Server Details
Taiwan payments (ECPay 綠界 + NewebPay 藍新) & e-invoices for AI agents. Stateless, never holds funds.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.1/5 across 4 of 4 tools scored.
Each tool has a clearly distinct purpose: creating payment links, voiding invoices, issuing invoices, and querying payment status. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern (e.g., create_payment_link, invalid_einvoice), making the naming predictable.
With 4 tools, the server is well-scoped for the payments and e-invoice domain, covering essential operations without unnecessary bloat.
The tool set covers core workflows (create payment, issue invoice, void invoice, check status), but lacks payment cancellation or invoice update, which are minor gaps.
Available Tools
4 toolscreate_payment_linkAInspect
Create a Taiwan payment link (credit card / ATM / convenience store) in TWD. Returns a URL the buyer opens to pay. Supports multiple Taiwan payment gateways — ECPay 綠界 (default; works instantly in a zero-setup demo sandbox, no credentials needed) and NewebPay 藍新金流 (bring your own credentials). Pick with the provider field, or just send a gateway's credential headers and it is auto-selected. Money always flows buyer→gateway→merchant; this service never touches funds.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Amount in TWD (integer, e.g. 500) | |
| provider | No | Payment gateway. "ecpay" (綠界, default; has a zero-setup demo sandbox) or "newebpay" (藍新金流; requires your own x-newebpay-* credential headers, no public sandbox). If omitted, auto-selected from which credential headers you send (defaults to ecpay). | |
| item_name | No | Item name shown to the buyer on the checkout page. Defaults to description. | |
| notify_url | No | Optional https webhook for server-to-server payment notification to YOUR server. If omitted, use query_payment_status to check payment state instead. | |
| return_url | No | Optional https URL to redirect the buyer to after payment. For ECPay the order id is appended as ?trade_no= | |
| description | Yes | What this payment is for (internal trade description, ≤200 chars) | |
| choose_payment | No | Payment methods offered to the buyer. Default ALL. (TWQR is ECPay-only; NewebPay maps Credit/ATM/CVS/BARCODE.) | |
| customer_email | No | Optional buyer email (used by NewebPay to email the payment result). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate mutation. Description adds safety context: 'never touches funds,' explains auto-selection and credential requirements. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two efficient sentences front-loading purpose, then key behavioral details. Could slightly tighten, but no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description covers return URL, payment flows, provider nuances, and notification options. Fully addresses tool complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all params (100%). Description adds value: explains provider auto-detection, TWQR limitation, notify_url fallback. Enhances schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description precisely states the tool creates a Taiwan payment link with specific payment methods and returns a URL. Clearly distinguishes from sibling tools via explicit mention of payment vs invoice/status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explains when to use, provider selection, auto-detection, and fallback to query_payment_status. Lacks explicit when-not-to-use, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
invalid_einvoiceADestructiveIdempotentInspect
Void (作廢) a previously issued ECPay e-invoice. Needs the invoice number and its issue date.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | Void reason (≤20 chars) | |
| invoice_no | Yes | Invoice number returned by issue_einvoice (e.g. AB12345678) | |
| invoice_date | Yes | Invoice date as returned by issue_einvoice (yyyy-MM-dd) |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and idempotentHint=true, so the description's 'Void' aligns. The description adds no extra behavioral context beyond that, which is acceptable for a simple operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no wasted words. Front-loaded with purpose, then input hint.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple void operation with clear schema and annotations. Lacks mention of expected outcomes (e.g., no return value or error cases) but output schema is absent, so not required. Sibling tools are not directly related.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all parameters with descriptions (100% coverage). The description mentions the key parameters but omits 'reason' as needed, though schema makes it clear. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action (void a previously issued ECPay e-invoice), specifies the resource, and the need for invoice number and date. Distinguishes from sibling tools which are for payment links, issuance, and querying.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use (to void a previously issued invoice) and what inputs are needed. Does not mention when not to use or alternatives, but context is sufficient given siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
issue_einvoiceAInspect
Issue a Taiwan government e-invoice (電子發票, B2C) via ECPay. Taiwan law requires an invoice for every sale; this tool issues one and (in production) uploads it to the Ministry of Finance. Works instantly in demo mode (ECPay official sandbox). Supports personal invoices (cloud carrier), company invoices with tax ID (統一編號), and donation.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | Invoice line items | |
| tax_id | No | 8-digit Taiwan company tax ID (統一編號) for a company invoice. Omit for personal invoice. | |
| carrier_num | No | Mobile barcode carrier (手機條碼載具, format /XXXXXXX). If omitted, ECPay member carrier is used. | |
| sales_amount | Yes | Invoice total in TWD including tax. Must equal the sum of item price×count. | |
| customer_name | No | Buyer name. Required when tax_id is given. | |
| relate_number | No | Your unique reference (≤30 chars). Auto-generated if omitted. | |
| customer_email | No | Buyer email (invoice notification). Required unless customer_phone is given. | |
| customer_phone | No | Buyer mobile number. Required unless customer_email is given. | |
| donation_love_code | No | Charity love code (愛心碼) to donate the invoice. Mutually exclusive with tax_id / carrier. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds beyond annotations: uploads to Ministry of Finance in production, works instantly in demo mode, and supports three invoice types. Annotations already show readOnlyHint=false and destructiveHint=false, consistent with the description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences that front-load purpose then add context. Efficient but could be slightly more structured (e.g., separate demo note).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers legal context, demo mode, and three use cases. No output schema, so return value explanation omitted but acceptable. With 9 params fully documented, description adds high-level completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for each parameter. The general description adds context (e.g., 'cloud carrier') but does not significantly enhance understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool issues Taiwan government e-invoices via ECPay, specifying B2C, and lists supported invoice types (personal, company, donation). It distinguishes from siblings by focusing on the invoicing act within the Taiwan legal context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage from legal requirement: 'Taiwan law requires an invoice for every sale; this tool issues one.' No explicit when-not-to-use or comparison with siblings like invalid_einvoice or create_payment_link.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_payment_statusARead-onlyInspect
Check whether a payment (created by create_payment_link) has been paid. Queries the gateway directly — a reliable pull-based alternative to webhooks. Works for ECPay 綠界 and NewebPay 藍新金流.
| Name | Required | Description | Default |
|---|---|---|---|
| provider | No | The gateway the link was created with. Must match create_payment_link. Defaults to ecpay (or auto-selected from credential headers). | |
| amount_twd | No | The original payment amount in TWD. REQUIRED for NewebPay 藍新 (its query API verifies by amount); ignored by ECPay. | |
| merchant_trade_no | Yes | The merchant_trade_no returned by create_payment_link |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description's statement 'Queries the gateway directly' is consistent. It adds value by noting reliability and gateway-specific behavior beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three short sentences, front-loaded with the main purpose, and no superfluous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool lacks an output schema, and the description does not explain what the output (e.g., status text, boolean) looks like. It covers purpose, parameters, and gateways but misses return value details, leaving some gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description does not add significant new meaning to parameters beyond the schema descriptions. The baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks payment status for a payment created by create_payment_link. It distinguishes itself from sibling tools by specifying it is for payment queries, not invoice or creation operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates when to use this tool as a pull-based alternative to webhooks and specifies supported gateways (ECPay, NewebPay). It does not explicitly mention when not to use, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!