Building Your First MCP Server: Exposing Internal Tools to AI Agents Safely

Описание и применение

Создание сервера MCP на TypeScript, который безопасно предоставляет внутренние инструменты для AI‑агентов, используя строгие схемы ввода, только чтение по умолчанию, создание только ожидающих запросов возврата и аудит всех вызовов.

Задача

Expose internal order lookup and refund request tools to AI agents while ensuring safety and auditability.

Результат

A functional MCP server that safely exposes internal tools, with audit logging and strict schemas, enabling AI agents to interact without risking unintended actions.

Рабочий процесс

• 1. Initialize project with npm and TypeScript.
• 2. Install @modelcontextprotocol/sdk, zod, and dev dependencies.
• 3. Add "type":"module" to package.json and create src/index.ts.
• 4. Import McpServer, StdioServerTransport, zod, audit, and backend functions.
• 5. Create McpServer instance with name and version.
• 6. Register "lookup_order" tool with title, description, inputSchema (orderId regex), outputSchema (orderId, status, totalCents, itemCount), and annotations (readOnlyHint).
• 7. Implement async handler: fetch order via getOrder, audit call, return error or structured result.
• 8. Register transport (StdioServerTransport) and connect server.
• 9. Log server running message.
• 10. (Optional) Extend with refund request tool following similar pattern.

Доказательства

Instead of writing a custom integration for every model and every client, you write one MCP server, and any MCP-capable client can discover and call its tools.

Источник

apply safety patterns from the start: strict input schemas, read-only by default, write actions that only create pending requests, and an audit log of every call.

Источник

server.registerTool("lookup_order", { title: "Look up an order", description: "Returns status, items and totals for one order. Read-only.", ...});

Источник