How does agent-twitter-client-mcp authenticate with Twitter?
It supports three methods: cookie authentication (recommended), username/password with optional 2FA, and Twitter API v2 credentials.
@theo-nash
基本信息
Model Context Protocol implementation for twitter interactions
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"twitter-mcp-server-theo-nash": {
"command": "npx",
"args": [
"agent-twitter-client-mcp"
]
}
}
}Fetch tweets from a specific user
Fetch a specific tweet by ID
Search for tweets
Post a new tweet
Post a tweet with a poll
Like a tweet
Retweet a tweet
Quote a tweet
Get a user's profile
Follow a user
Get a user's followers
Get users a user is following
Chat with Grok via Twitter
Check the health of the Twitter MCP server
It integrates with Twitter using the agent-twitter-client package, allowing AI models to interact with Twitter without direct API access. It's for developers and AI agents that need to perform Twitter actions programmatically.
Install via npm globally or locally, configure Twitter credentials in a .env file, then run the MCP server with agent-twitter-client-mcp or npx agent-twitter-client-mcp. Alternatively, configure it as an MCP server in Claude Desktop by adding the appropriate configuration to the claude_desktop_config.json file.
It supports three methods: cookie authentication (recommended), username/password with optional 2FA, and Twitter API v2 credentials.
It requires Node.js and npm. For Grok integration, agent-twitter-client v0.0.19 or higher is required.
Data is accessed through the MCP server using your Twitter credentials; the server itself does not store data persistently beyond the session.
Yes, Twitter imposes rate limits. Grok has specific limits: 25 messages per 2 hours for non-premium accounts; premium accounts have higher limits.
Yes, you can configure it as an MCP server in Claude Desktop's configuration file with the appropriate environment variables for authentication.
TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g
28-tool MCP server for web scraping, crawling, deep research & autonomous extraction — clean Markdown & structured JSON for Claude, Cursor & any MCP client. 1,000 free one-time credits, local-Ollama LLM support.

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai
Model Context Protocol (MCP) server for Hostinger API. If you don't want to install or run anything locally, connect directly to Hostinger's hosted MCP server: This opens a browser window to authorize via OAuth. Once app

Instant blogs for AI agents: a publishing CMS with no dashboard. One signup call returns a blog, an API key and a live URL; then publish markdown posts and get public URLs back.
评论