Twitter▌

by ryanmac
Automate tweet operations, manage profiles, and enable auto tweet post with this TypeScript server for Twitter. Supports
Provides a TypeScript-based server for interacting with Twitter, enabling tweet operations, user profile management, and Grok AI integration through multiple authentication methods.
best for
- / AI assistants managing social media accounts
- / Developers building Twitter automation tools
- / Social media managers scheduling content
- / Researchers collecting Twitter data
capabilities
- / Create Twitter posts and threads
- / Reply to specific tweets by ID
- / Follow users by username
- / Retrieve user profiles and recent tweets
- / Search tweets with custom queries
- / Get account information and user IDs
what it does
Connects to Twitter/X to post tweets, reply to posts, follow users, and retrieve profile data. Supports both credential-based and API authentication methods.
about
Twitter is a community-built MCP server published by ryanmac that provides AI assistants with tools and capabilities via the Model Context Protocol. Automate tweet operations, manage profiles, and enable auto tweet post with this TypeScript server for Twitter. Supports It is categorized under communication.
how to install
You can install Twitter in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
license
MIT
Twitter is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
readme
agent-twitter-client-mcp
A Model Context Protocol (MCP) server that integrates with Twitter using the agent-twitter-client package, allowing AI models to interact with Twitter without direct API access.
Features
-
Authentication Options:
- Cookie-based authentication (recommended)
- Username/password authentication
- Twitter API v2 credentials
-
Tweet Operations:
- Fetch tweets from users
- Get specific tweets by ID
- Search tweets
- Send tweets with text and media
- Create polls
- Like, retweet, and quote tweets
-
User Operations:
- Get user profiles
- Follow users
- Get followers and following lists
-
Grok Integration:
- Chat with Grok via Twitter's interface
- Continue conversations with conversation IDs
- Get web search results and citations
- Access Twitter's real-time data through Grok
- Note: Grok functionality requires agent-twitter-client v0.0.19 or higher
Documentation
- Developer Guide - Comprehensive guide for developers
- Testing Guide - Instructions for testing the MCP
- Agent Guide - Guide for AI agents on how to use the Twitter MCP
- Contributing Guide - Guidelines for contributing to this project
- Changelog - History of changes to this project
- Demo README - Guide for running the demo scripts
- Grok Examples - Documentation for the Grok AI integration examples
Quick Start
Installation
# Install globally
npm install -g agent-twitter-client-mcp
# Or install locally
npm install agent-twitter-client-mcp
Basic Usage
- Create a
.envfile with your Twitter credentials (see Authentication Methods) - Run the MCP server:
# If installed globally
agent-twitter-client-mcp
# If installed locally
npx agent-twitter-client-mcp
Demo Scripts
The package includes a demo directory with example scripts that demonstrate various features:
# Clone the repository to access the demo scripts
git clone https://github.com/ryanmac/agent-twitter-client-mcp.git
cd agent-twitter-client-mcp/demo
# Run the interactive demo menu
./run-demo.sh
# Run a specific demo script
./run-demo.sh --script tweet-search.js
# Run Grok AI examples (requires agent-twitter-client v0.0.19)
./run-demo.sh --script simple-grok.js --use-local-agent-twitter-client
./run-demo.sh --script grok-chat.js --use-local-agent-twitter-client
See the Demo README for more details.
Port Configuration
By default, the MCP server runs on port 3000. If you need to change this (for example, if you already have an application running on port 3000), you have several options:
Option 1: Using Environment Variables
Set the PORT environment variable:
PORT=3001 npx agent-twitter-client-mcp
Option 2: Using Docker Compose
If using Docker Compose, you can configure both the host and container ports in your .env file:
# .env file
MCP_HOST_PORT=3001 # The port on your host machine
MCP_CONTAINER_PORT=3000 # The port inside the container
Then run:
docker-compose up -d
This will map port 3001 on your host to port 3000 in the container, allowing you to access the MCP at http://localhost:3001 while your other application continues to use port 3000.
Setup with Claude Desktop
- Configure Claude Desktop to use this MCP by adding to your config file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"agent-twitter-client-mcp": {
"command": "npx",
"args": ["-y", "agent-twitter-client-mcp"],
"env": {
"AUTH_METHOD": "cookies",
"TWITTER_COOKIES": "["auth_token=YOUR_AUTH_TOKEN; Domain=.twitter.com", "ct0=YOUR_CT0_VALUE; Domain=.twitter.com", "twid=u%3DYOUR_USER_ID; Domain=.twitter.com"]"
}
}
}
}
- Restart Claude Desktop
Authentication Methods
Cookie Authentication (Recommended)
{
"AUTH_METHOD": "cookies",
"TWITTER_COOKIES": "["auth_token=YOUR_AUTH_TOKEN; Domain=.twitter.com", "ct0=YOUR_CT0_VALUE; Domain=.twitter.com", "twid=u%3DYOUR_USER_ID; Domain=.twitter.com"]"
}
To obtain cookies:
- Log in to Twitter in your browser
- Open Developer Tools (F12)
- Go to the Application tab > Cookies
- Copy the values of
auth_token,ct0, andtwidcookies - Make sure to include the
Domain=.twitter.compart for each cookie
Username/Password Authentication
{
"AUTH_METHOD": "credentials",
"TWITTER_USERNAME": "your_username",
"TWITTER_PASSWORD": "your_password",
"TWITTER_EMAIL": "your_email@example.com", // Optional
"TWITTER_2FA_SECRET": "your_2fa_secret" // Optional, required if 2FA is enabled
}
Twitter API Authentication
{
"AUTH_METHOD": "api",
"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"
}
Available Tools
get_user_tweets: Fetch tweets from a specific userget_tweet_by_id: Fetch a specific tweet by IDsearch_tweets: Search for tweetssend_tweet: Post a new tweetsend_tweet_with_poll: Post a tweet with a polllike_tweet: Like a tweetretweet: Retweet a tweetquote_tweet: Quote a tweetget_user_profile: Get a user's profilefollow_user: Follow a userget_followers: Get a user's followersget_following: Get users a user is followinggrok_chat: Chat with Grok via Twitterhealth_check: Check the health of the Twitter MCP server
Testing Interface
The MCP includes an interactive command-line interface for testing:
npx agent-twitter-client-mcp-test
# or if installed locally
npm run test:interface
This launches a REPL where you can test various MCP functions:
agent-twitter-client-mcp> help
Available commands:
health Run a health check
profile <username> Get a user profile
tweets <username> [count] Get tweets from a user
tweet <id> Get a specific tweet by ID
search <query> [count] Search for tweets
post <text> Post a new tweet
like <id> Like a tweet
retweet <id> Retweet a tweet
quote <id> <text> Quote a tweet
follow <username> Follow a user
followers <userId> [count] Get a user's followers
following <userId> [count] Get users a user is following
grok <message> Chat with Grok
help Show available commands
exit Exit the test interface
Example Test Commands
# Run a health check
agent-twitter-client-mcp> health
# Search for tweets
agent-twitter-client-mcp> search mcp 2
# Get a user's profile
agent-twitter-client-mcp> profile elonmusk
# Get tweets from a user
agent-twitter-client-mcp> tweets openai 5
# Chat with Grok
agent-twitter-client-mcp> grok Explain quantum computing in simple terms
Example Usage
Ask Claude to:
- "Search Twitter for tweets about AI"
- "Post a tweet saying 'Hello from Claude!'"
- "Get the latest tweets from @OpenAI"
- "Chat with Grok about quantum computing"
Advanced Usage
Working with Media
To post a tweet with an image:
I want to post a tweet with an image. The tweet should say "Beautiful sunset today!" and include this image.
To post a tweet with a video:
I want to post a tweet with a video. The tweet should say "Check out this amazing video!" and include the video file.
Creating Polls
To create a poll:
Create a Twitter poll asking "What's your favorite programming language?" with options: Python, JavaScript, Rust, and Go. The poll should run for 24 hours.
Interacting with Grok
To have a conversation with Grok:
Use Grok to explain quantum computing to me. Ask it to include some real-world applications.
To continue a conversation with Grok:
Continue the Grok conversation and ask it to elaborate on quantum entanglement.
Grok's Unique Capabilities
Grok on Twitter has access to real-time Twitter data that even the standalone Grok API doesn't have. This means you can ask Grok about:
- Current trending topics on Twitter
- Analysis of recent tweets on specific subjects
- Information about Twitter users and their content
- Real-time events being discussed on the platform
Example queries:
- "What are the trending topics on Twitter right now?"
- "Analyze the sentiment around AI on Twitter"
- "What are people saying about the latest Apple event?"
- "Show me information about popular memecoins being discussed today"
Grok Authentication Requirements
Grok functionality requires proper authentication. The MCP supports two methods:
-
Cookie Authentication (Recommended):
- Cookies must be in JSON array format
- Example:
TWITTER_COOKIES=["auth_token=YOUR_AUTH_TOKEN; Domain=.twitter.com", "ct0=YOUR_CT0_VALUE; Domain=.twitter.com", "twid=u%3DYOUR_USER_ID; Domain=.twitter.com"] - Essential cookies are
auth_token,ct0, andtwid
-
Username/Password Authentication:
- Set
TWITTER_USERNAMEandTWITTER_PASSWORDin your environment - May encounter Cloudflare protection in some cases
- Set
Grok Rate Limits
Grok has rate limits that may affect usage:
- Non-premium accounts: 2