About Twitter MCP Server
Twitter MCP Server is an MCP server that gives AI agents access to Twitter functions, built on the agent-twitter-client library. It offers read, interaction, posting and timeline operations through one consistent tool interface for AI assistants.
Key features
- 01Reading user tweets and profiles
- 02Searching tweets by keyword or hashtag
- 03Liking, retweeting and following users
- 04Posting tweets, replies, quotes and threads
- 05Timeline, list and trending topic access
- 06Image and video upload for posts
Use cases
- 01Letting an AI assistant search tweets on a given topic
- 02Fetching profiles or list tweets for analysis
- 03Drafting and publishing tweets or threads through an AI assistant
MCP support
This project is an MCP server that exposes Twitter tools such as get_tweets, search_tweets and post_tweet to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMETwitter MCP Server
A powerful Twitter integration for AI agents that leverages the Model Context Protocol (MCP) standard, providing a comprehensive set of Twitter functionality through a clean and consistent interface.
Overview
This server provides access to Twitter's features through MCP tools, allowing seamless integration with AI assistants and other MCP-compatible clients. It's built on top of the agent-twitter-client library and provides robust error handling, rate limiting, and consistent response formatting.
Features
Basic Reading
- Get tweets from users with media support
- Fetch user profiles with detailed information
- Search tweets by hashtags or keywords
- Filter search results by latest/top
- Rate limiting (max 50 tweets per request)
User Interactions
- Like/Unlike tweets
- Retweet/Undo retweet
- Post tweets with:
- Text content
- Media attachments (images, videos)
- Reply functionality
- Quote tweet capability
Advanced Features
- Get user relationships (followers/following)
- Fetch trending topics
- Access different timeline types:
- Home timeline
- Following timeline
- User timeline
- List management (fetch list tweets)
Media & Advanced Interactions
- Media handling:
- Image upload (JPEG, PNG, GIF)
- Video upload (MP4)
- Alt text support
- Thread creation
- Follow/Unfollow users
Tools
Reading Tools
get_tweets- Fetch recent tweets from a userget_profile- Get a user's profile informationsearch_tweets- Search for tweets by hashtag or keyword
Interaction Tools
like_tweet- Like or unlike a tweetretweet- Retweet or undo retweetpost_tweet- Post a new tweet with optional mediacreate_thread- Create a Twitter thread
Timeline Tools
get_timeline- Get tweets from different timeline typesget_list_tweets- Get tweets from a Twitter listget_trends- Get current trending topics
User Management Tools
get_user_relationships- Get followers or following listfollow_user- Follow or unfollow a user
Installation
- Install dependencies:
npm install
- Build the server:
npm run build
- Configure environment variables:
# Required: Twitter Account Credentials (for user authentication)
TWITTER_USERNAME=your_username
TWITTER_PASSWORD=your_password
TWITTER_EMAIL=your_email
# Twitter API Authentication (Optional)
TWITTER_API_KEY=your_api_key
TWITTER_API_SECRET_KEY=your_api_secret_key
TWITTER_ACCESS_TOKEN=your_access_token
TWITTER_ACCESS_TOKEN_SECRET=your_access_token_secret
- Add the server config to your MCP client:
On MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
On Windows:
%APPDATA%/Claude/claude_desktop_config.json
Configuration:
{
"mcpServers": {
"twitter-mcp-server": {
"command": "/path/to/twitter-mcp-server/build/index.js"
}
}
}
Development
For development with auto-rebuild:
npm run watch
Debugging
Since MCP servers communicate over stdio, you can use the MCP Inspector for debugging:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Error Handling
The server implements comprehensive error handling:
- Input validation for all parameters
- Rate limiting protection
- Detailed error messages
- Proper error propagation
- Logging for debugging
Response Format
All tools return responses in a consistent format:
{
content: [{
type: "text",
text: string // JSON stringified response or error message
}]
}
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - see LICENSE file for details
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.