
X MCP Server
Enables users to interact with X (Twitter) through the X API. Supports posting tweets, retrieving user timelines, searching tweets, and replying to tweets with comprehensive error handling.
README
X MCP Server
A Model Context Protocol (MCP) server for posting tweets to X (Twitter) and interacting with the X API.
<a href="https://glama.ai/mcp/servers/@krishna-paulraj/x-mcp-server"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@krishna-paulraj/x-mcp-server/badge" alt="X Server MCP server" /> </a>
Features
- Post Tweets: Create and post tweets to X (Twitter)
- Get User Timeline: Retrieve your recent tweets
- Search Tweets: Search for tweets using queries
- Reply to Tweets: Reply to existing tweets
- Error Handling: Comprehensive error handling and validation
Prerequisites
-
X Developer Account: You need a Twitter/X developer account
- Go to Twitter Developer Portal
- Create a new app and get your API credentials
-
Node.js: Version 18 or higher
Setup
-
Clone and Install Dependencies:
npm install
-
Configure Environment Variables:
cp env.example .env
Edit
.env
and add your X API credentials:X_API_KEY=your_api_key_here X_API_SECRET=your_api_secret_here X_ACCESS_TOKEN=your_access_token_here X_ACCESS_TOKEN_SECRET=your_access_token_secret_here
-
Build the Project:
npm run build
Usage
Running the Server
# Development mode
npm run dev
# Production mode
npm start
Available Tools
The server provides the following tools:
1. post_tweet
Post a new tweet to X.
Parameters:
text
(required): The tweet content (max 280 characters)reply_to_tweet_id
(optional): ID of the tweet to reply to
Example:
{
"text": "Hello, world! This is my first tweet via MCP! 🚀",
"reply_to_tweet_id": "1234567890123456789"
}
2. get_user_timeline
Get your recent tweets.
Parameters:
count
(optional): Number of tweets to retrieve (default: 10, max: 100)
Example:
{
"count": 5
}
3. search_tweets
Search for tweets using a query.
Parameters:
query
(required): Search querycount
(optional): Number of results (default: 10, max: 100)
Example:
{
"query": "MCP protocol",
"count": 20
}
MCP Client Configuration
To use this server with an MCP client, add it to your client configuration:
{
"mcpServers": {
"x-server": {
"command": "node",
"args": ["dist/index.js"],
"env": {
"X_API_KEY": "your_api_key",
"X_API_SECRET": "your_api_secret",
"X_ACCESS_TOKEN": "your_access_token",
"X_ACCESS_TOKEN_SECRET": "your_access_token_secret"
}
}
}
}
Development
Project Structure
x-mcp-server/
├── src/
│ └── index.ts # Main server implementation
├── dist/ # Compiled JavaScript (generated)
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── env.example # Environment variables template
└── README.md # This file
Scripts
npm run build
: Compile TypeScript to JavaScriptnpm start
: Run the compiled servernpm run dev
: Run in development mode with hot reloadnpm test
: Run tests (when implemented)
Error Handling
The server includes comprehensive error handling for:
- Missing API credentials
- Invalid tweet content (length, format)
- API rate limits
- Network errors
- Invalid parameters
Security Notes
- Never commit your
.env
file to version control - Keep your API credentials secure
- Use environment variables for all sensitive data
- Consider using a
.gitignore
file to exclude sensitive files
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details.
Support
For issues and questions:
- Check the error messages for common issues
- Verify your API credentials are correct
- Ensure you have the necessary X API permissions
- Check the X API documentation for rate limits and restrictions
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。