AXT-MCP

AXT-MCP

A Model Context Protocol service registry and connector framework that enables seamless integration with multiple services and models through a standardized API interface. Provides an extensible architecture for custom service adapters, API integrations, and model registries.

Category
访问服务器

README

AXT-MCP

MCP service registry and connector framework for AXT.

Purpose

AXT-MCP is a Model Context Protocol (MCP) implementation designed to provide a flexible service registry and connector framework. It enables seamless integration with multiple services and models through a standardized API interface.

Setup

Prerequisites

  • Node.js 16.x or higher
  • npm or yarn package manager

Installation

npm install

Configuration

Edit mcp.config.yaml to configure your service registry and model settings.

Running the Server

npm start

The server will start on the default port (3000) or the port specified in your environment variables.

Supported Connectors

Connectors are located in /src/connectors/. Currently, the framework supports extensible connector architecture for:

  • Custom service adapters
  • API integrations
  • Model registries

Additional connectors can be added by implementing the connector interface.

API Reference

Endpoints

API routes are defined in /src/routes/. The framework provides a RESTful API structure:

  • Health check endpoint
  • Registry operations
  • Connector management

Detailed API documentation will be added as routes are implemented.

Syncing with Notion & Atlas

Overview

AXT-MCP provides integration capabilities with Notion databases and MongoDB Atlas, enabling seamless synchronization of use case datasets and other structured data across platforms.

Notion Integration

The Notion connector (src/connectors/notionSync.js) provides bidirectional sync functionality:

Setup

  1. Create a Notion Integration

    • Go to https://www.notion.so/my-integrations
    • Create a new integration and copy your API token
    • Share your target database with the integration
  2. Configure Environment Variables

    NOTION_API_KEY=your_notion_integration_token
    NOTION_DATABASE_ID=your_database_id
    
  3. Update mcp.config.yaml

    • Add your Notion workspace configuration (see config file for details)

Usage

const { syncNotionData, fetchNotionRecords, pushNotionRecord } = require('./src/connectors/notionSync');

// Fetch records from Notion
const records = await fetchNotionRecords('your-database-id');

// Push a record to Notion
const newRecord = await pushNotionRecord('your-database-id', {
  'Name': { title: [{ text: { content: 'Use Case 1' } }] },
  'Status': { select: { name: 'Active' } }
});

// Bidirectional sync
const syncResults = await syncNotionData({
  databaseId: 'your-database-id',
  direction: 'bidirectional',
  mcpRecords: localDataset
});

API References

  • Notion API Documentation: https://developers.notion.com/
  • Query Database: https://developers.notion.com/reference/post-database-query
  • Create Page: https://developers.notion.com/reference/post-page
  • Update Page: https://developers.notion.com/reference/patch-page

Atlas Integration

MongoDB Atlas integration enables cloud-based data persistence and advanced querying:

Setup

  1. Create an Atlas Cluster

    • Sign up at https://www.mongodb.com/cloud/atlas
    • Create a new cluster (free tier available)
    • Whitelist your IP address
  2. Configure Connection String

    ATLAS_CONNECTION_STRING=mongodb+srv://username:password@cluster.mongodb.net/dbname
    
  3. Add Atlas Configuration to mcp.config.yaml

    • See the atlas section in the config file

Usage

// Atlas connector to be implemented in src/connectors/atlasSync.js
// Follow similar pattern as notionSync.js

Cross-Platform Workflow

For seamless data flow across platforms:

  1. Notion → MCP → Atlas

    • Fetch structured data from Notion databases
    • Transform and validate through MCP
    • Store in Atlas for analytics and persistence
  2. Atlas → MCP → Notion

    • Query processed data from Atlas
    • Transform to Notion format
    • Push updates back to Notion for team collaboration

Automation Notes

Scheduled Syncs

Use cron jobs or task schedulers to automate regular syncs:

// Example: Sync every hour
const cron = require('node-cron');

cron.schedule('0 * * * *', async () => {
  console.log('Running scheduled Notion sync...');
  await syncNotionData({
    databaseId: process.env.NOTION_DATABASE_ID,
    direction: 'bidirectional'
  });
});

Webhook Integration

For real-time syncs, consider implementing webhooks:

  • Notion doesn't natively support webhooks, but you can poll for changes
  • Atlas supports change streams for real-time data updates

Error Handling

  • All sync operations include error tracking
  • Failed records are logged in the sync results
  • Implement retry logic for transient failures

Best Practices

  • Rate Limiting: Respect Notion API rate limits (3 requests per second)
  • Incremental Syncs: Use timestamps to sync only changed records
  • Data Validation: Validate data schemas before pushing
  • Backup: Maintain backups before bulk operations
  • Monitoring: Log all sync operations for audit trails

Additional Resources

  • Notion API SDK: npm install @notionhq/client
  • MongoDB Node Driver: npm install mongodb
  • Environment Variables: Use .env files with dotenv package

Contributing

We welcome contributions to AXT-MCP! To contribute:

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/your-feature-name)
  3. Commit your changes (git commit -am 'Add new feature')
  4. Push to the branch (git push origin feature/your-feature-name)
  5. Create a Pull Request

Development Guidelines

  • Follow existing code style and conventions
  • Add tests for new features

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选