xmcp Application
A template/starter project for building MCP servers with structured directories for tools, prompts, and resources that are automatically discovered and registered.
README
xmcp Application
This project was created with create-xmcp-app.
Getting Started
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm dev
This will start the MCP server with the selected transport method.
Project Structure
This project uses the structured approach where tools, prompts, and resources are automatically discovered from their respective directories:
src/tools- Tool definitionssrc/prompts- Prompt templatessrc/resources- Resource handlers
Tools
Each tool is defined in its own file with the following structure:
import { z } from "zod";
import { type InferSchema, type ToolMetadata } from "xmcp";
export const schema = {
name: z.string().describe("The name of the user to greet"),
};
export const metadata: ToolMetadata = {
name: "greet",
description: "Greet the user",
annotations: {
title: "Greet the user",
readOnlyHint: true,
destructiveHint: false,
idempotentHint: true,
},
};
export default function greet({ name }: InferSchema<typeof schema>) {
return `Hello, ${name}!`;
}
Prompts
Prompts are template definitions for AI interactions:
import { z } from "zod";
import { type InferSchema, type PromptMetadata } from "xmcp";
export const schema = {
code: z.string().describe("The code to review"),
};
export const metadata: PromptMetadata = {
name: "review-code",
title: "Review Code",
description: "Review code for best practices and potential issues",
role: "user",
};
export default function reviewCode({ code }: InferSchema<typeof schema>) {
return `Please review this code: ${code}`;
}
Resources
Resources provide data or content with URI-based access:
import { z } from "zod";
import { type ResourceMetadata, type InferSchema } from "xmcp";
export const schema = {
userId: z.string().describe("The ID of the user"),
};
export const metadata: ResourceMetadata = {
name: "user-profile",
title: "User Profile",
description: "User profile information",
};
export default function handler({ userId }: InferSchema<typeof schema>) {
return `Profile data for user ${userId}`;
}
Adding New Components
Adding New Tools
To add a new tool:
- Create a new
.tsfile in thesrc/toolsdirectory - Export a
schemaobject defining the tool parameters using Zod - Export a
metadataobject with tool information - Export a default function that implements the tool logic
Adding New Prompts
To add a new prompt:
- Create a new
.tsfile in thesrc/promptsdirectory - Export a
schemaobject defining the prompt parameters using Zod - Export a
metadataobject with prompt information and role - Export a default function that returns the prompt text
Adding New Resources
To add a new resource:
- Create a new
.tsfile in thesrc/resourcesdirectory - Use folder structure to define the URI (e.g.,
(users)/[userId]/profile.ts→users://{userId}/profile) - Export a
schemaobject for dynamic parameters (optional for static resources) - Export a
metadataobject with resource information - Export a default function that returns the resource content
Building for Production
To build your project for production:
npm run build
# or
yarn build
# or
pnpm build
This will compile your TypeScript code and output it to the dist directory.
Running the Server
You can run the server for the transport built with:
- HTTP:
node dist/http.js - STDIO:
node dist/stdio.js
Given the selected transport method, you will have a custom start script added to the package.json file.
For HTTP:
npm run start-http
# or
yarn start-http
# or
pnpm start-http
For STDIO:
npm run start-stdio
# or
yarn start-stdio
# or
pnpm start-stdio
Learn More
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。