Korea Payments (Toss Payments — cards / KakaoPay·NaverPay / virtual accounts)
Server Details
Korea payments for AI agents — card, KakaoPay/NaverPay, 가상계좌 via Toss Payments. 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 4.5/5 across 3 of 3 tools scored.
Each tool has a clear, distinct purpose: creating a payment, confirming it, and checking status. No overlap or ambiguity.
All tool names follow verb_noun pattern (confirm_payment, create_payment_link, query_payment_status) consistently, making them predictable.
Three tools cover the essential workflow for Korea payments: create, confirm, and query. This is well-scoped and not excessive or minimal.
The core payment lifecycle is covered: create, confirm, and query. Minor gap: no explicit cancel tool, but cancelation may be handled via status or external actions. Still sufficient for typical integration.
Available Tools
3 toolsconfirm_paymentAIdempotentInspect
Complete (approve) a Korea payment after the buyer authenticated in the Toss Payments checkout window. Required final step of the Toss flow: call this within 10 minutes of the buyer finishing (status IN_PROGRESS), passing the same payment_key, order_id and amount used at creation — the amount match is a built-in tamper check. On success status becomes DONE (or WAITING_FOR_DEPOSIT for virtual accounts until the buyer deposits).
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | The exact amount (KRW) used at creation — mismatch rejects the confirmation | |
| order_id | Yes | The order_id of the payment | |
| payment_key | Yes | The payment_key returned by create_payment_link |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds significant behavioral context beyond annotations: time constraint, tamper-check via amount match, status transitions (DONE, WAITING_FOR_DEPOSIT). Does not cover error cases or retry behavior, but idempotent hint is annotated.
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 sentences, each earning its place: purpose, usage instructions with timing and constraints, and outcome statuses. No fluff.
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?
Well-rounded for a simple confirmation tool: explains flow, constraints, and statuses. Could mention error states or retry implications given idempotentHint, but the description is largely 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 description adds value by explaining that parameters must match those used at creation and that amount serves as a tamper check, beyond what the schema descriptions provide.
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 that the tool completes/approves a Korea payment, specifying the context of Toss Payments and distinguishing it from sibling tools like create_payment_link and query_payment_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?
Provides clear context: call within 10 minutes of buyer finishing, with status IN_PROGRESS, using same parameters as creation. Does not explicitly list when not to use or alternatives, but the guidance is 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 Korea payment link in KRW via Toss Payments (토스페이먼츠), a major Korean payment gateway. Methods: card (카드 — the checkout window also shows easy-pay wallets like KakaoPay 카카오페이 / NaverPay 네이버페이 / Toss Pay when enabled on the merchant contract), virtual_account (가상계좌), transfer (계좌이체 instant bank transfer), mobile_phone (휴대폰 carrier billing). Returns a hosted checkout URL the buyer opens. IMPORTANT Toss flow: after the buyer authenticates in the checkout window, you MUST call confirm_payment within 10 minutes to complete the payment (poll query_payment_status; when status is IN_PROGRESS, confirm). Bring your own Toss Payments secret key via the x-toss-secret-key header (free test keys from developers.tosspayments.com; test_sk_/test_gsk_ keys never move real money). Money always flows buyer→Toss Payments→merchant; this service never touches funds.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Amount in KRW (integer, e.g. 10000 = ₩10,000). Minimum 100. | |
| method | No | Payment method. Default "card" (window includes easy-pay wallets per merchant contract). "virtual_account" = 가상계좌, "transfer" = instant bank transfer, "mobile_phone" = carrier billing. | |
| fail_url | No | Optional https URL for failed/cancelled authentication. Defaults to a hosted result page on this server. | |
| order_id | No | Your unique order reference (6-64 chars, alphanumeric and -_=). Auto-generated if omitted. | |
| order_name | Yes | Name of the order shown to the buyer (≤100 chars, e.g. "생수 외 1건") | |
| success_url | No | Optional https URL Toss redirects the buyer to after authentication succeeds (paymentKey/orderId/amount appended as query params). Defaults to a hosted result page on this server. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description discloses critical behavioral traits beyond annotations: the creation of a payment link, the need to subsequently confirm payment, the 10-minute window, and the money flow (buyer->Toss->merchant, service never touches funds). Annotations indicate write operation and non-destructive, which aligns; 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?
Description is relatively long due to necessary details about payment flow, methods, and authentication. However, it is well-structured with clear sections (methods, important flow, key requirements). Could be slightly more concise but effectively communicates essential 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 the complexity of Toss Payments integration and absence of output schema, the description is remarkably complete. It explains creation, authentication, confirmation steps, headers, and money flow. Adequate for an AI agent to invoke correctly.
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 description coverage is 100%, providing baseline 3. Description adds value by listing method options with Korean names, example of order_name, and clarification that success_url redirects with query parameters. This enriches 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 it creates a Korea payment link in KRW via Toss Payments, lists specific payment methods, and mentions the returned hosted checkout URL. It distinguishes from sibling tools (confirm_payment and query_payment_status) by describing the creation step and the post-authentication flow.
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?
Description provides explicit usage instructions: after buyer authentication, must call confirm_payment within 10 minutes after polling query_payment_status. It also advises bringing a Toss Payments secret key via header. Though it does not explicitly state when not to use this tool, the instructions are clear and sufficient for correct usage.
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 the status of a Korea payment (created by create_payment_link). Fetches the payment from Toss Payments directly — a reliable pull-based alternative to webhooks. Statuses: READY (buyer has not finished), IN_PROGRESS (buyer authenticated — call confirm_payment within 10 minutes!), WAITING_FOR_DEPOSIT (virtual account issued, awaiting deposit), DONE (paid), CANCELED / PARTIAL_CANCELED / ABORTED / EXPIRED.
| Name | Required | Description | Default |
|---|---|---|---|
| order_id | No | Alternatively, the order_id (only finds the payment after it has been confirmed/approved) | |
| payment_key | No | The payment_key returned by create_payment_link (preferred) |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds that it 'Fetches the payment from Toss Payments directly,' confirming the pull-based nature. 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?
Description is concise with two sentences plus a status list. The list is slightly lengthy but informative. Could be more structured, but 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?
No output schema, so the status list fills that gap. Mentions alternative to webhooks. Lacks details on authentication or rate limits, but annotations cover safety. Adequate given 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 coverage is 100%, but the description adds value by noting that payment_key is 'preferred' and that order_id 'only finds the payment after it has been confirmed/approved.' This aids correct parameter selection.
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 'Check the status of a Korea payment (created by create_payment_link).' The verb 'check' and resource 'payment status' are specific. It also distinguishes from siblings by being a read-only pull-based check, not a confirmation or 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?
Provides explicit context: 'a reliable pull-based alternative to webhooks.' Guides on when to use each status, including an urgent call-to-action for IN_PROGRESS: 'call confirm_payment within 10 minutes!' Also recommends payment_key as preferred.
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!