Which integrations are available for this server?

Provides a module for [NestJS](/mcp/servers/integrations/nestjs) to create an MCP (Model Context Protocol) server with Server-Sent Events (SSE) transport, allowing services to be exposed as tools that clients can discover and execute. Enables sending continuous [progress](/mcp/servers/integrations/progress) updates from tools to clients, allowing for tracking of long-running operations with percentage completion indicators. Integrates [Zod](/mcp/servers/integrations/zod) schema validation for tool requests, enabling type-safe parameter validation for tools exposed through the MCP server.

NestJS MCP Server Module

A NestJS module to effortlessly expose tools, resources, and prompts for AI, from your NestJS applications using the Model Context Protocol (MCP).

With @rekog/mcp-nest you define tools, resources, and prompts in a way that's familiar in NestJS and leverage the full power of dependency injection to utilize your existing codebase in building complex enterprise ready MCP servers.

Features

🚀 Multi-Transport Support: HTTP+SSE, Streamable HTTP, and STDIO
🔧 Tools: Expose NestJS methods as MCP tools with automatic discovery and Zod validation
- 🛠️ Elicitation: Interactive tool calls with user input elicitation
- 📊 Progress Notifications: Real-time progress updates for long-running operations
- 🌐 HTTP Request Access: Full access to request context within MCP handlers
📁 Resources: Serve content and data through MCP resource system
📚 Resource Templates: Dynamic resources with parameterized URIs
💬 Prompts: Define reusable prompt templates for AI interactions
🔐 Guard-based Authentication: Guard-based security with OAuth support
🏠 Built-in Authorization Server — Using the built-in Authorization Server for easy setups. (Beta)
🌐 External Authorization Server — Securing your MCP server with an external authorization server (Keycloak, Auth0, etc).
💉 Dependency Injection: Leverage NestJS DI system throughout MCP components

Are you interested to build ChatGPT widgets (with the OpenAI SDK)? Find out how to do that with @rekog/MCP-Nest in this repository MCP-Nest-Samples/pizzaz-openai-apps-sdk

Related MCP server: SSE MCP Server

Installation

npm install @rekog/mcp-nest @modelcontextprotocol/sdk zod@^3

Optional dependencies

If you use the built-in authorization server with the TypeORM store, install the following optional peer dependencies:

npm install @nestjs/typeorm typeorm

Quick Start

// app.module.ts import { Module } from '@nestjs/common'; import { McpModule } from '@rekog/mcp-nest'; import { GreetingTool } from './greeting.tool'; @Module({ imports: [ McpModule.forRoot({ name: 'my-mcp-server', version: '1.0.0', }), ], providers: [GreetingTool], }) export class AppModule {}

// greeting.tool.ts import { Injectable } from '@nestjs/common'; import { Tool, Context } from '@rekog/mcp-nest'; import { z } from 'zod'; @Injectable() export class GreetingTool { @Tool({ name: 'greeting-tool', description: 'Returns a greeting with progress updates', parameters: z.object({ name: z.string().default('World'), }), }) async sayHello({ name }, context: Context) { await context.reportProgress({ progress: 50, total: 100 }); return `Hello, ${name}!`; } }

Documentation

Tools Guide - Define and expose NestJS methods as MCP tools
Resources Guide - Serve static and dynamic content
Resource Templates Guide - Create parameterized resources
Prompts Guide - Build reusable prompt templates
Built-in Authorization Server - Secure your MCP server with built-in OAuth
External Authorization Server - Securing your MCP server with an external authorization server (Keycloak, Auth0, etc)
Server examples - MCP servers examples (Streamable HTTP, HTTP, and STDIO) and with Fastify support