xendit-mcp
xendit-mcp
Xendit 결제 API를 위한 Model Context Protocol 서버입니다. 인도네시아, 필리핀, 태국, 베트남, 말레이시아 전역의 인보이스, 지급, 잔액 및 거래를 지원합니다.
설치
npm install -g xendit-mcp또는 npx xendit-mcp를 사용하여 필요할 때 실행하세요.
Related MCP server: rippr
구성
Xendit 대시보드에 가입하세요.
설정(Settings) → API 키로 이동하여 키를 생성하세요.
개발용으로는 테스트 키(
xnd_development_...)를, 운영용으로는 라이브 키를 사용하세요.
변수 | 필수 | 설명 |
| 예 | 테스트 또는 라이브 API 키 |
| 아니오 | 지급 도구(자금 이동)를 활성화하려면 |
| 아니오 | 라이브/운영 키( |
Claude Desktop
claude_desktop_config.json을 편집하세요:
{
"mcpServers": {
"xendit": {
"command": "npx",
"args": ["-y", "xendit-mcp"],
"env": {
"XENDIT_API_KEY": "your-api-key"
}
}
}
}Claude Code
claude mcp add xendit -e XENDIT_API_KEY=your-api-key -- npx -y xendit-mcpCursor
Claude Desktop과 동일한 형식으로 ~/.cursor/mcp.json에 추가하세요.
도구
도구 | 설명 |
| 유형별(CASH, HOLDING, TAX) 계좌 잔액 조회. |
| 상태, 날짜 범위 또는 통화별로 필터링된 인보이스 목록. |
| 단일 인보이스 조회. |
| 결제 인보이스를 생성하고 결제 링크를 반환. |
| 활성 인보이스 만료 처리. |
| 결제, 지급, 환불 및 수수료 목록. |
| 은행 계좌나 전자지갑으로 자금 송금. |
| 지급 상태 확인. |
| 국가별 지원 은행 및 전자지갑 목록. |
프롬프트
프롬프트 | 설명 |
| 계좌 잔액 보고. |
| 지난 N일 동안 받은 결제 내역. |
| 고객을 위한 결제 링크 생성. |
| 미결제 인보이스 목록. |
| 오늘의 결제 활동 요약. |
리소스
리소스 | URI | 설명 |
지원 은행 |
| 인도네시아 및 필리핀 은행 코드. |
API 정보 |
| Xendit API 세부 정보 및 속도 제한. |
예시 쿼리
What's my current Xendit balance?
Saldo Xendit saya berapa?
Create an invoice for Rp 500,000 for "Website design deposit".
Buatkan invoice Rp 500.000 untuk "Deposit desain website".
Show me all unpaid invoices.
Tampilkan semua invoice yang belum dibayar.
XENDIT_ENABLE_DISBURSEMENTS=true 설정 시:
Send Rp 1,000,000 to Ahmad at BCA.
Kirim Rp 1.000.000 ke Ahmad di BCA.
List available banks for disbursement in the Philippines.환경
Xendit은 테스트 API 키와 라이브 API 키를 별도로 발행합니다. 테스트 키는 Xendit 샌드박스 환경에서 작동하므로 실제 자금이 이동하지 않습니다. 라이브 키(xnd_production_..., iluma_production_..., sk_live_...)는 운영 환경에서 작동합니다.
안전성
이 서버는 Xendit API를 통해 실제 자금을 이동시킬 수 있습니다. 주요 안전 장치는 다음과 같습니다:
지급 도구는 기본적으로 비활성화되어 있습니다.
create_disbursement,get_disbursement,list_disbursement_banks는XENDIT_ENABLE_DISBURSEMENTS=true일 때만 등록됩니다. 신뢰할 수 없는 콘텐츠에 의해 도구 입력값이 영향을 받을 수 없는 신뢰된 에이전트 환경에서만 활성화하십시오.라이브 키는 기본적으로 거부됩니다.
xnd_production_,iluma_production_또는sk_live_접두사가 있는 키는XENDIT_ALLOW_LIVE=true가 아닌 경우 시작 시 거부됩니다. 항상 개발용 키(xnd_development_...)로 먼저 테스트하십시오.멱등성(Idempotency).
create_disbursement는externalId를Idempotency-Key로 사용하므로, 동일한externalId로 재시도해도 중복 이체가 생성되지 않습니다. 새로운 지급 건마다 새로운externalId를 사용하십시오.
이러한 안전 장치가 있더라도 도구 호출을 승인하기 전에 자금 이동 요청을 검토하십시오. 모델 출력에서 파생된 도구 입력값은 신뢰할 수 없는 것으로 간주하십시오.
면책 조항
이 서버는 커뮤니티에서 구축한 비공식 MCP 서버입니다. Xendit과 제휴, 보증 또는 후원 관계가 없습니다. Xendit은 해당 소유자의 상표입니다. 사용자의 책임하에 사용하십시오. 작성자는 오용, 프롬프트 인젝션 또는 버그로 인해 발생한 자금 손실에 대해 어떠한 책임도 지지 않습니다.
라이선스
Available Tools
6 toolsget_balanceARead-only
Get your Xendit account balance. Returns available balance by account type (CASH, HOLDING, TAX).
| Name | Required | Description | Default |
|---|---|---|---|
| currency | No | Currency code (e.g., IDR, PHP). Defaults to your account's primary currency. | |
| accountType | No | Account type to check | CASH |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, and the description adds that the tool returns available balance by account type, which is consistent and adds value beyond annotations. No 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?
Two concise sentences, front-loaded with the purpose, with no extraneous information. Every word is justified.
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 read tool with full schema and annotations. However, the lack of output schema means the description could add return format details, but it is sufficient.
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%, so baseline is 3. The description does not add new parameter-level details beyond what the schema already provides (e.g., default currency, account type enum).
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 verb 'Get' and resource 'Xendit account balance', and specifies return by account types (CASH, HOLDING, TAX). This distinguishes it from sibling tools like get_invoice or list_transactions.
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?
No explicit guidance on when to use versus alternatives or when not to use. The purpose is clear, but the description lacks explicit context for selection among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_invoiceARead-only
Get details of a specific Xendit invoice by ID.
| Name | Required | Description | Default |
|---|---|---|---|
| invoiceId | Yes | Xendit invoice ID |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true. Description adds minimal behavioral context beyond stating it returns 'details'. No mention of error behavior or what details include.
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?
Single sentence, front-loaded with key information, no redundant words. Efficient and to the point.
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 get-by-id operation with one required parameter and readOnlyHint, the description is complete. No output schema is expected, and sibling tools don't require additional context.
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 for invoiceId is clear ('Xendit invoice ID'). Description does not add further semantics beyond the schema. With 100% schema coverage, 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?
Description clearly states 'Get details of a specific Xendit invoice by ID' with a specific verb and resource. It distinguishes from siblings like list_invoices which lists multiple invoices.
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?
No explicit when-to-use or alternatives are mentioned. Usage is implied for retrieving a single invoice by ID, but no guidance is given for scenarios like missing invoice or comparison with list_invoices.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_workspace_modeWorkspace ModeARead-only
Explain the current Xendit MCP mode, what actions are enabled, and the safest next step to enable more access.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond the readOnlyHint annotation: it discloses that the tool explains the mode, actions enabled, and a recommended next step. This aligns with the annotation and provides useful transparency.
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 a single concise sentence that clearly states the tool's purpose and outputs. Every part is necessary and 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 the tool has no parameters, is read-only, and no output schema, the description sufficiently covers what the tool does and what it returns. No additional context is needed for correct usage.
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 zero parameters, the description does not need to add parameter details. The baseline for 0 params is 4, and the description fulfills it by explaining what the tool does without needing parameter input.
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 the tool explains the current Xendit MCP mode, actions enabled, and next step for more access. This is a specific verb+resource that distinguishes it from sibling tools like get_balance or get_invoice which deal with different resources.
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 clearly implies the usage context: when you need to understand the current mode and possible next steps. However, it does not explicitly state when not to use or mention alternatives, though given the unique purpose, this is a minor gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
guided_setupGuided SetupARead-only
Generate a safe Claude Code or Claude Desktop setup snippet for read-only, invoices, or guarded payouts mode. Uses a form when the client supports MCP elicitation.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Desired user-facing mode | |
| client | No | Target client | |
| allowLive | No | Set true only if you intend to use a live Xendit key | |
| serverName | No | Claude MCP server name, defaults to xendit | |
| maxDailyAmount | No | Only used for guarded-payouts mode | |
| allowedAccounts | No | Comma-separated CHANNEL_CODE:ACCOUNT_NUMBER entries for guarded-payouts mode | |
| maxDisbursementAmount | No | Only used for guarded-payouts mode |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, so the agent knows this is a safe read operation. Description adds that the snippet is 'safe' and mentions form elicitation, but doesn't add substantive behavioral traits beyond what annotations provide.
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 short sentences that front-load the purpose. No redundant information; every word earns its place.
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?
With 7 parameters (0 required), two enums, and no output schema, the description covers the core functionality. Could mention output format or more about allowLive context, but siblings are all queries so the role is clear.
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% (all parameters documented in schema). Description does not add additional meaning beyond schema, so baseline is 3.
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 it generates a safe setup snippet for three specific modes (read-only, invoices, guarded-payouts). Distinct from sibling tools which are all retrieval/query tools, so no ambiguity.
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 context about generating snippets and using forms when client supports MCP elicitation, but does not explicitly state when to use this tool versus alternatives or mention when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_invoicesARead-only
List invoices from your Xendit account with optional filters for status, date range, and pagination.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of invoices to return (1-100) | |
| status | No | Filter by invoice status | |
| currency | No | Filter by currency (IDR, PHP, etc.) | |
| createdAfter | No | Return invoices created after this ISO 8601 timestamp. Must be used with createdBefore. | |
| createdBefore | No | Return invoices created before this ISO 8601 timestamp. Must be used with createdAfter. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and description confirms read-only listing. Adds filter context but does not explain pagination mechanics or result set behavior.
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?
Single sentence, 16 words, no redundant information. Front-loaded with verb and resource.
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 basic listing and filters. Missing details on pagination and return format, but for a simple tool with no output schema, it is sufficiently 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% with descriptions for all 5 parameters. Description groups filters but adds no extra meaning 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 it lists invoices from Xendit account with optional filters, distinguishing it from sibling get_invoice (single invoice) and list_transactions (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?
Lacks explicit guidance on when to use this tool versus alternatives like get_invoice or list_transactions. No exclusions or when-not-to-use context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_transactionsARead-only
List transactions from your Xendit account. Includes payments received, payouts, refunds, transfers, and balance adjustments.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of transactions (1-50) | |
| types | No | Filter by transaction type | |
| status | No | Filter by transaction status | |
| currency | No | Filter by currency | |
| createdGte | No | Created on or after (ISO 8601) | |
| createdLte | No | Created on or before (ISO 8601) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate read-only, which aligns with the description. However, the description adds no further behavioral details such as pagination, rate limits, or potential side effects.
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?
A single sentence that is front-loaded with the main action and includes essential details without 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?
The description covers the purpose but does not describe the return format or any output schema, leaving the agent uncertain about the response structure.
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%, so the description adds no additional meaning beyond the schema. The description lists transaction types, but they are already in the enum.
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 'List transactions' with the resource and includes a comprehensive list of transaction types, distinguishing it from siblings like get_balance and get_invoice.
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?
While the description implies usage for listing multiple transactions, it lacks explicit guidance on when to use this tool versus alternatives like get_invoice for specific transactions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
9 tool updates
v0.2.0- Removed
create_disbursement - Removed
create_invoice - Removed
expire_invoice - Removed
get_disbursement - Added
get_workspace_mode - Added
guided_setup - Removed
list_disbursement_banks - Changed
list_invoices2 fields changed- changed
Input schema / properties / createdAfter / descriptionPrevious value: -"Return invoices created after this date (ISO 8601, e.g., 2025-01-01T00:00:00Z)"New value: +"Return invoices created after this ISO 8601 timestamp. Must be used with createdBefore." - changed
Input schema / properties / createdBefore / descriptionPrevious value: -"Return invoices created before this date (ISO 8601)"New value: +"Return invoices created before this ISO 8601 timestamp. Must be used with createdAfter."
- Changed
list_transactions3 fields changed- changed
Input schema / properties / status / descriptionPrevious value: -"Filter by status"New value: +"Filter by transaction status" - changed
Input schema / properties / status / enumPrevious value: -[ - "SUCCESS", - "PENDING", - "FAILED", - "VOIDED" -]New value: +[ + "PENDING", + "SUCCESS", + "FAILED", + "VOIDED", + "REVERSED" +] - changed
Input schema / properties / types / enumPrevious value: -[ - "PAYMENT", - "DISBURSEMENT", - "REFUND", - "FEE", - "ADJUSTMENT" -]New value: +[ + "ADJUSTMENT_ADD", + "ADJUSTMENT_DEDUCT", + "BNPL_PARTNER_SETTLEMENT_CREDIT", + "BNPL_PARTNER_SETTLEMENT_DEBIT", + "CASHBACK_FEE", + "CASHBACK_VAT", + "CHARGEBACK", + "CONVERSION", + "DISBURSEMENT", + "FOREX_DEDUCTION", + "FOREX_DEPOSIT", + "IN_PERSON_PAYMENT", + "LOAN_REPAYMENT", + "OTHER", + "PAYMENT", + "REFUND", + "REMITTANCE", + "REMITTANCE_COLLECTION_PAYMENT", + "REMITTANCE_PAYOUT", + "RESERVES_HOLD", + "RESERVES_RELEASE", + "TOPUP", + "TRANSFER_IN", + "TRANSFER_OUT", + "WITHDRAWAL" +]
9 tool updates
v1.0.0- First observed
create_disbursement - First observed
create_invoice - First observed
expire_invoice - First observed
get_balance - First observed
get_disbursement - First observed
get_invoice - First observed
list_disbursement_banks - First observed
list_invoices - First observed
list_transactions
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: balance retrieval, invoice details, workspace mode explanation, setup snippet generation, and listing of invoices and transactions. No overlap between tools.
Most tools follow a verb_noun pattern using snake_case (e.g., get_balance, list_invoices). The only minor deviation is 'guided_setup' which is adjective_noun, but it remains clear and consistent with the overall style.
Six tools is well-scoped for a payment service MCP server covering essential read operations, account balance, and setup guidance. It's neither too few nor too many.
The tool surface is limited to read and setup operations, missing write capabilities like create/update/delete invoices or payouts. This creates notable gaps for a payment API, restricting agents to passive data retrieval.
Maintenance
Related MCP Connectors
MCP server for Modern Treasury — payment orders, transactions, counterparties and ledgers.
MCP server for Codat — companies, connections, invoices, bills and financial statements.
MCP server for Quaderno — tax-rate calculation, invoices, contacts, products, receipts & expenses.
MCP Server for agents to onboard, pay, and provision services autonomously with InFlow
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables interaction with Velo Payments APIs for global payment operations, automatically generated using AG2's MCP builder from the Velo Payments OpenAPI specification.-
- AlicenseAqualityBmaintenanceExtract YouTube transcripts for AI agents, RAG pipelines, and LLM workflows. Supports any YouTube URL. Returns clean text or timestamped segments. No API keys required.14MIT
- AlicenseAqualityAmaintenanceMCP server for Rakuten APIs. Search products, books, hotels, and rankings across Japan's largest e-commerce platform.2894 npm5MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for Paper.id Indonesian invoicing and accounting platform, providing 31 tools for partner and invoice management, QRIS payments, and reporting with automatic token refresh.-