Hong Kong Payments (Stripe — Alipay / WeChat Pay)
Server Details
Hong Kong payments for AI agents — Alipay / WeChat Pay via Stripe. 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 4.4/5 across 6 of 6 tools scored.
Each tool has a clearly distinct purpose: creating payment links, creating subscription links, querying payment status, querying subscription status, refunding payments, and canceling subscriptions. There is no overlap or ambiguity.
All tool names follow a consistent verb_noun pattern with underscores (e.g., create_payment_link, query_subscription), making them predictable and easy to understand.
With 6 tools covering the core operations of payment and subscription lifecycle management, the count is well-scoped and appropriate for the server's purpose.
The tool set covers the essential payment and subscription workflow (creation, query, refund, cancel). Minor omissions like listing all payments or subscriptions exist, but they are not critical for the primary use cases.
Available Tools
6 toolscancel_subscriptionADestructiveIdempotentInspect
Cancel a subscription. By default the subscription stays active until the end of the current paid period (fair to the buyer); pass immediate=true to cancel right now.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | session_id (cs_...) or subscription_id (sub_...) | |
| immediate | No | true = cancel immediately. Default false = cancel at period end. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds behavioral context beyond annotations: explains default behavior (end of period) and immediate cancellation. No contradiction with destructiveHint=true.
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 sentences, no wasted words. Front-loaded with action and key detail about fairness.
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?
For a simple mutation tool with 2 params and no output schema, the description adequately covers behavior and parameter details. Could mention that cancellation is irreversible.
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%, but description adds meaning by clarifying id accepts session_id or subscription_id, and immediate defaults to false with effect explained.
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 'Cancel a subscription' with a specific verb and resource. It distinguishes from siblings like refund_payment and query_subscription by focusing on cancellation with optional immediate flag.
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?
Provides clear guidance on when to use immediate=true vs default, and mentions fairness to buyer. No explicit exclusion of alternatives, but implied context sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create_payment_linkAInspect
Create a payment link in HKD for Hong Kong via Stripe (Checkout Sessions). Buyer pays with cards, Apple Pay, Alipay, WeChat Pay — whatever is enabled on the Stripe account. Returns a hosted checkout URL the buyer opens to pay — payment completes automatically, no confirm step. Bring your own credentials via HTTP header (x-stripe-secret-key; free test credentials from dashboard.stripe.com never move real money). Money always flows buyer→Stripe→merchant; this service never touches funds. Optional: issue_invoice=true auto-creates a VAT-ready invoice (PDF + hosted page, emailed to the buyer) after payment; collect_tax_id=true collects the buyer's business tax ID (e.g. EU VAT number) at checkout and puts it on the invoice.
| Name | Required | Description | Default |
|---|---|---|---|
| amount_hkd | Yes | Amount in HKD (decimals allowed), e.g. 40. Minimum 4. | |
| description | Yes | What this payment is for (shown to the buyer, ≤200 chars) | |
| success_url | No | Optional https URL to send the buyer to after payment. | |
| issue_invoice | No | true = Stripe automatically creates and emails a post-payment invoice (PDF + hosted invoice page). Ideal for B2B / VAT bookkeeping. Note: Stripe charges a small Invoicing fee per invoice issued. | |
| collect_tax_id | No | true = ask the buyer for their business tax ID (e.g. EU VAT number) on the checkout page; it appears on the invoice. Combine with issue_invoice for a VAT-compliant receipt. | |
| customer_email | No | Optional buyer email. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations, discloses that payment completes automatically, requires credentials via header, money flows buyer→Stripe→merchant (service never touches funds), and explains optional invoice/tax ID behavior. No contradiction with 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?
Well-structured with front-loaded purpose, then flow details, then optional features. Every sentence provides value, though slightly long; could be tightened slightly without losing 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?
Given no output schema, description covers return value (hosted checkout URL), payment flow, credentials, money handling, and optional features. Adequately complete for complex tool with 6 parameters.
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?
Adds substantial meaning beyond schema: explains amount min/max, description length, optional success_url, and provides extra context for issue_invoice (Stripe fee) and collect_tax_id (combines with invoice). Schema coverage is 100% but description enriches it.
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 verb (Create), resource (payment link), currency (HKD), and region (Hong Kong) via Stripe Checkout Sessions. Distinguishes from sibling tools like create_subscription_link by focusing on one-time payments.
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?
Provides good context on when to use: for one-time HKD payments, with supported payment methods. Mentions optional invoicing and tax ID. However, lacks explicit exclusion of other currencies or direct comparison to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create_subscription_linkAInspect
Create a recurring subscription checkout link (monthly/yearly/weekly billing) via Stripe. The buyer opens the URL, enters their card once, and is then charged automatically every period until canceled. Amount is per billing period in the local currency major unit. Respects the same owner policy guardrails as payments (the per-period amount is checked before anything is created).
| Name | Required | Description | Default |
|---|---|---|---|
| interval | No | Billing period. Default "month". | |
| amount_hkd | Yes | Amount charged per billing period (local currency major unit) | |
| description | Yes | What the subscription is for (shown to the buyer, <=200 chars) | |
| success_url | No | Optional https URL to send the buyer to after subscribing. | |
| customer_email | No | Optional buyer email (pre-filled at checkout; receipt goes there). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description reveals that the tool creates a subscription link, the buyer enters card once and is charged periodically, and it respects the same owner policy guardrails. Annotations indicate it is not read-only or destructive, and the description adds the checkout flow and per-period amount check. However, it omits potential rate limits or failure scenarios.
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 two sentences that front-load the main action and then provide essential details without waste. Every sentence adds value.
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 description covers the creation and usage well but does not specify the return value (e.g., the generated URL). With no output schema, this is a gap. It also lacks information on whether the subscription is created immediately or upon payment, which could be ambiguous.
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?
With 100% schema coverage, the description adds context by explaining the billing flow and that the amount is per period. It clarifies the interval options (monthly/yearly/weekly) although the schema also includes 'day'. The description reinforces the meaning of amount_hkd and description, adding value 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?
The description clearly states the tool creates a recurring subscription checkout link via Stripe. It specifies the billing interval options (monthly/yearly/weekly) and distinguishes it from one-time payment tools like create_payment_link.
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 explains that the link is for recurring billing and that the buyer is charged automatically. It implies when to use it but does not explicitly contrast with sibling tools like create_payment_link for one-time payments, though the context of recurring vs. one-time is clear.
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 Hong Kong payment (created by create_payment_link) has been paid. Queries Stripe directly — pull-based, no webhook needed. paid=true when status is PAID. If the payment was created with issue_invoice=true, the result also includes invoice_url and invoice_pdf once paid.
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | The session_id returned by create_payment_link |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true; the description adds that it queries Stripe directly and provides conditional invoice fields, but does not disclose rate limits or other behavioral traits.
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 two concise sentences that front-load the core purpose and add a key detail about conditional output, with no wasted 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?
For a simple read-only tool with one parameter and no output schema, the description covers the main output (paid boolean, conditional invoice fields) and context, though it omits error cases or other status values.
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?
With 100% schema coverage and a single parameter, the description adds context by specifying the session_id comes from create_payment_link, going beyond the schema's basic description.
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 whether a Hong Kong payment has been paid, specifying the condition (paid=true when status is PAID) and distinguishing it from sibling tools like create_payment_link and refund_payment.
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 explains this is a pull-based check without webhooks, implying when to use it, but does not explicitly state when not to use it or compare with alternatives like query_subscription.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_subscriptionARead-onlyInspect
Check a subscription created by create_subscription_link. Accepts the session_id (cs_...) or subscription_id (sub_...). active=true when the subscription is ACTIVE or TRIALING; NOT_SUBSCRIBED_YET means the buyer has not completed checkout.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | session_id (cs_...) returned by create_subscription_link, or subscription_id (sub_...) |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds value beyond annotations by explaining the 'active' field behavior and the 'NOT_SUBSCRIBED_YET' status. Annotations already indicate read-only and open-world, so description complements without contradiction.
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 concise, front-loaded sentences covering purpose, input syntax, and output interpretation. No redundant 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?
Covers purpose, input, and key output behavior. Lacks mention of error cases or rate limits, but given the tool's simplicity and lack of output schema, it is nearly complete.
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 repeats the schema's parameter description exactly. No additional semantic value 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?
Clearly states the tool checks a subscription created by create_subscription_link. The verb 'check' and resource 'subscription' are specific, and it distinguishes itself from siblings like cancel_subscription (action) or query_payment_status (different resource).
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?
Implies usage for checking subscriptions after creation, and notes accepted ID types, but does not explicitly state when not to use it or provide alternatives. No direct comparison to siblings like cancel_subscription.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
refund_paymentADestructiveInspect
Refund a paid payment (created by create_payment_link). Full refund by default; pass amount for a partial refund where supported. Refunds respect the same owner policy guardrails (x-agentpay-max-amount) as payments — the amount is checked before anything is sent to the gateway.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | No | Optional partial-refund amount in the local currency major unit. Omit for a full refund. | |
| session_id | Yes | The session_id of the paid payment (same id used by query_payment_status) |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds valuable context: refunds check the x-agentpay-max-amount guardrail before sending to gateway, and partial refunds are supported where applicable. This goes beyond the annotations without contradicting them.
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, each serving a purpose: action & scope, default/partial behavior, and guardrails. No extraneous information, well-structured with key details front-loaded.
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?
Given no output schema, the description doesn't address return values, but it covers input behavior, guardrails, and default/partial refund. Some minor gaps (e.g., what happens if partial refund not supported), but overall sufficient for a well-annotated, simple tool.
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 both parameters. The description adds meaning by clarifying default behavior (full refund without amount) and that amount is for partial refunds. It also links session_id to query_payment_status, reinforcing its role.
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 explicitly states 'Refund a paid payment' and specifies that it applies to payments created by create_payment_link. This clearly identifies the action and resource, distinguishing it from sibling tools like query_payment_status (status check) and create_payment_link (creation).
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 explains default behavior (full refund) and how to do partial refunds by passing amount. It also notes that refunds respect the same owner policy guardrails as payments, providing context on when this tool is appropriate. However, it does not explicitly state when not to use it or mention alternatives like voids.
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!