Stripeサブスクリプション、コールごとのクレジット課金、x402暗号資産決済を、課金コードを書くことなくあらゆるMCPサーバーに追加できます。
MCP Billing Gatewayは、AIエージェントとMCPサーバーの間に配置されるホスト型課金プロキシです。支払い検証、利用状況の追跡、プラン制限の適用を自動的に処理します。サーバーを登録し、料金プランを設定して、呼び出し元をプロキシURLに向けるだけです。課金コードは不要です。
ライブサービス: https://mcp-billing-gateway-production.up.railway.app
pip install mcp-billing-gatewayまたは uvx を使用する場合:
uvx mcp-billing-gateway~/Library/Application Support/Claude/claude_desktop_config.json (macOS) または %APPDATA%\Claude\claude_desktop_config.json (Windows) に追加します:
{
"mcpServers": {
"mcp-billing-gateway": {
"command": "uvx",
"args": ["mcp-billing-gateway"]
}
}
}プロジェクト内の .cursor/mcp.json に追加します:
{
"mcpServers": {
"mcp-billing-gateway": {
"command": "uvx",
"args": ["mcp-billing-gateway"]
}
}
}設定を追加した後、エディタを再起動してMCPサーバーを有効にしてください。
Related MCP server: Agent Bazaar
ツール | 説明 |
| サービスの機能、サポートされている支払い方法、機能、統合ドキュメントを返します |
ローカルのMCPサーバーはサービスディスカバリを提供します。完全な課金機能はホスト型ゲートウェイ上で実行されます。オペレーターとして登録し、MCPサーバーをプロキシ経由で運用してください。
AI Agent → MCP Billing Gateway → Your MCP Server
(billing enforced here)オペレーターとして登録し、APIキーを取得する
MCPサーバーのURLと料金プランを登録する
呼び出し元をプロキシスラッグに向ける: https://mcp-billing-gateway-production.up.railway.app/proxy/{your-slug}/mcp
呼び出し元はStripe APIキーまたはx402 USDCで支払う — 課金は透過的に処理されます
コールごとの課金 — ツール呼び出しごとに課金（法定通貨または暗号資産）
サブスクリプション — コール制限付きの月額/年額Stripeプラン
段階的価格設定 — 無料プラン + 利用状況に応じた有料プラン
x402マイクロペイメント — APIキーなしでAIエージェントからBase上のUSDCを受け入れ可能
オペレーターダッシュボード — 収益、利用状況、呼び出し元をリアルタイムで追跡
MCPトランスポート — /mcp/ エンドポイントでの完全なStreamable HTTP MCPトランスポート
curl -X POST https://mcp-billing-gateway-production.up.railway.app/api/v1/operator/register \
-H "Content-Type: application/json" \
-d '{"email": "you@example.com", "name": "Your Name"}'レスポンス:
{
"operator_id": "op_abc123",
"api_key": "bg_live_xxxxxxxxxxxx",
"message": "Operator registered successfully"
}curl -X POST https://mcp-billing-gateway-production.up.railway.app/api/v1/servers \
-H "Authorization: Bearer bg_live_xxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"name": "My MCP Server",
"upstream_url": "https://your-mcp-server.com/mcp",
"proxy_slug": "my-server"
}'curl -X POST https://mcp-billing-gateway-production.up.railway.app/api/v1/servers/{server_id}/plans \
-H "Authorization: Bearer bg_live_xxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"name": "Pay as you go",
"billing_model": "per_call",
"price_per_call_usd_micro": 10000,
"free_calls_per_month": 100
}'{
"mcpServers": {
"my-server": {
"url": "https://mcp-billing-gateway-production.up.railway.app/proxy/my-server/mcp",
"headers": {
"Authorization": "Bearer CALLER_API_KEY"
}
}
}
}方法 | 最適な用途 | 方法 |
Stripeサブスクリプション | 人間の開発者 | Stripe Checkout経由の月額または年額プラン |
Stripeコールごと課金 | 人間の開発者 | ツール呼び出しごとにクレジットを消費 |
x402マイクロペイメント | AIエージェント | Base上のUSDC、APIキー不要 |
# Using the MCP client
result = await session.call_tool("get_billing_info")
print(result)
# {
# "service": "MCP Billing Gateway",
# "version": "0.1.0",
# "payment_methods": ["stripe_subscription", "stripe_metered", "x402_crypto"],
# "features": ["Per-call usage tracking", "Tiered pricing", ...],
# "live_service": "https://mcp-billing-gateway-production.up.railway.app"
# }# 1. Register
API_KEY=$(curl -s -X POST .../api/v1/operator/register \
-H "Content-Type: application/json" \
-d '{"email": "dev@example.com", "name": "Dev"}' | jq -r .api_key)
# 2. Add your server
SERVER_ID=$(curl -s -X POST .../api/v1/servers \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"name": "my-tool", "upstream_url": "https://my-tool.com/mcp", "proxy_slug": "my-tool"}' \
| jq -r .server_id)
# 3. Set pricing: $0.01 per call, 100 free calls/month
curl -X POST .../api/v1/servers/$SERVER_ID/plans \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"name": "Starter", "billing_model": "per_call", "price_per_call_usd_micro": 10000, "free_calls_per_month": 100}'
# Callers now connect via: .../proxy/my-tool/mcpダッシュボードへのアクセス:
https://mcp-billing-gateway-production.up.railway.app/dashboard収益、利用状況、アクティブな呼び出し元を追跡し、サーバーをリアルタイムで設定します。
エンドポイント | メソッド | 説明 |
| POST | オペレーターアカウントの作成 |
| GET | プロフィールとAPIキーの表示 |
| GET | 収益と利用統計 |
エンドポイント | メソッド | 説明 |
| POST | MCPサーバーの登録 |
| GET | サーバー一覧の取得 |
| POST | 料金プランの作成 |
エンドポイント | メソッド | 説明 |
| ANY | 課金制限付きのプロキシ呼び出し |
| ANY | Streamable HTTP MCPトランスポート |
┌─────────────┐ ┌──────────────────────┐ ┌──────────────────┐
│ AI Agent / │────▶│ MCP Billing Gateway │────▶│ Your MCP Server │
│ MCP Client │◀────│ (hosted on Railway) │◀────│ (upstream) │
└─────────────┘ └──────────────────────┘ └──────────────────┘
│
├── Payment verification (Stripe / x402)
├── Usage tracking & rate limiting
├── Tier enforcement
└── Operator dashboardゲートウェイは透過的なプロキシです。呼び出し元は通常通りMCPサーバーとやり取りします。ゲートウェイがリクエストをインターセプトし、支払いを検証し、利用状況を追跡して、アップストリームのサーバーに転送します。
ゲートウェイは上記のホスト型URLで利用可能です。セルフホスト環境の場合は、サーバーリポジトリをクローンし、Docker経由でデプロイしてください:
docker build -t mcp-billing-gateway .
docker run -p 3000:3000 mcp-billing-gatewayGet information about the MCP Billing Gateway service and integration options.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves information, implying a read-only operation, but fails to detail aspects like authentication needs, rate limits, response format, or error handling. This leaves significant gaps in understanding how the tool behaves.
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, efficient sentence that directly states the tool's function without unnecessary words. It is front-loaded with the core action and resource, making it easy to parse and understand quickly.
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 zero parameters, 100% schema coverage, and an output schema exists, the description's focus on purpose is adequate. However, it lacks behavioral details (e.g., response structure, error cases) that could enhance completeness, especially since no annotations are provided to fill those gaps.
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?
The tool has zero parameters, and the input schema coverage is 100%, so no parameter documentation is needed. The description appropriately does not discuss parameters, focusing instead on the tool's purpose, which aligns with the baseline expectation for parameterless tools.
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 action ('Get information') and target resource ('MCP Billing Gateway service and integration options'), making the purpose understandable. It lacks sibling tools for differentiation, but the scope is well-defined. No tautology or misleading elements are present.
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 guidance is provided on when to use this tool, such as for setup, troubleshooting, or comparison with other services. The description implies usage for general information retrieval but offers no context, alternatives, or exclusions, leaving the agent without operational direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.2get_billing_infoScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to confuse it with. The tool's purpose is clearly defined as retrieving billing information, making disambiguation trivial.
The single tool name 'get_billing_info' follows a clear verb_noun pattern (get + billing_info), which is consistent with itself. Since there are no other tools, there is no inconsistency to evaluate, and the naming is straightforward.
A single tool is too few for a server named 'MCP Billing Gateway SDK', which suggests a broader scope for managing billing operations. This minimal set likely leaves significant gaps in functionality, such as creating, updating, or deleting billing data, making it inappropriate for comprehensive billing tasks.
The tool set is severely incomplete for a billing gateway domain, as it only provides a read operation (get_billing_info) without any support for create, update, delete, or other essential billing workflows. This will cause agent failures when attempting to perform full billing lifecycle management.
MCP server integrating with Stripe - tools for customers, products, payments, and more.
Monetize any MCP server: x402 paywall, pay-per-call billing in USDC on Base, agent marketplace.
MCP server for Pinchwork - an agent-to-agent task marketplace with credits-based economy
