mcp-x-intelligence
Read-only X/Twitter research MCP server allowing AI assistants to search viral content, analyze accounts, track trends, and discover niche leaders without requiring the official X API.
README
mcp-x-intelligence
X/Twitter research MCP for Claude, Cursor, Windsurf and any MCP-compatible AI agent.
Search viral content, analyze accounts, track trends, and find niche leaders — all from your AI assistant. No posting. No DMs. Pure read-only research.
What it does
mcp-x-intelligence exposes four research tools over the Model Context Protocol (MCP):
- Search viral content — find posts that are blowing up around any keyword
- Analyze accounts — deep engagement metrics, top posts, best posting times
- Get trending topics — real-time trends by country
- Find niche leaders — discover top creators in any space
This is a research tool. It never posts, replies, or modifies anything on X.
Why not the official X API?
The official X API requires a developer account, a paid plan, and a complex OAuth setup. The cheapest tier that allows meaningful search access starts at $200+/month. For research and content strategy, that's overkill.
mcp-x-intelligence uses twitterapi.io — a third-party API that provides the same data at a fraction of the cost, with a simple API key (no OAuth dance).
Compatible clients
Works with any MCP-compatible AI agent:
| Client | Config file |
|---|---|
| Claude Desktop | claude_desktop_config.json |
| Claude Code | .claude/settings.json |
| Cursor | .cursor/mcp.json |
| Windsurf | mcp_config.json |
| Cline | VS Code settings |
| Codex CLI | ~/.codex/config.yaml |
| Gemini CLI | ~/.gemini/settings.json |
| Any MCP client | Standard config |
Quick start — BYOK
1. Get your API key
Sign up at twitterapi.io and grab your key from the dashboard.
2. Add to your MCP client
Choose your client below and replace tk_YOUR_KEY_HERE with your actual key.
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"x-intelligence": {
"url": "https://mcp-x-intelligence.<your-account>.workers.dev",
"headers": {
"x-twitterapi-key": "tk_YOUR_KEY_HERE"
}
}
}
}
Claude Code
{
"mcpServers": {
"x-intelligence": {
"url": "https://mcp-x-intelligence.<your-account>.workers.dev",
"headers": {
"x-twitterapi-key": "tk_YOUR_KEY_HERE"
}
}
}
}
Cursor
Edit .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:
{
"mcpServers": {
"x-intelligence": {
"url": "https://mcp-x-intelligence.<your-account>.workers.dev",
"headers": {
"x-twitterapi-key": "tk_YOUR_KEY_HERE"
}
}
}
}
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"x-intelligence": {
"url": "https://mcp-x-intelligence.<your-account>.workers.dev",
"headers": {
"x-twitterapi-key": "tk_YOUR_KEY_HERE"
}
}
}
}
Cline (VS Code)
In VS Code settings (settings.json):
{
"cline.mcpServers": {
"x-intelligence": {
"url": "https://mcp-x-intelligence.<your-account>.workers.dev",
"headers": {
"x-twitterapi-key": "tk_YOUR_KEY_HERE"
}
}
}
}
Gemini CLI
Edit ~/.gemini/settings.json:
{
"mcpServers": {
"x-intelligence": {
"url": "https://mcp-x-intelligence.<your-account>.workers.dev",
"headers": {
"x-twitterapi-key": "tk_YOUR_KEY_HERE"
}
}
}
}
Available tools
| Tool | Description |
|---|---|
search_viral_content |
Find viral posts by keyword with engagement filters (likes, retweets, time window) |
analyze_account |
Full account analysis: followers, engagement rate, top 5 posts, most active hours |
get_trending_topics |
Real-time trending topics by country (worldwide, USA, Spain, Mexico, Argentina, Colombia...) |
get_niche_leaders |
Find top accounts in any niche sorted by follower count |
Tool parameters
search_viral_content
query string required Search keyword or phrase
min_likes number optional Minimum likes (default: 50)
min_retweets number optional Minimum retweets (default: 0)
hours_back number optional Hours back to search (default: 48)
limit number optional Max results (default: 20)
analyze_account
username string required X username without @
tweets_limit number optional Tweets to analyze (default: 20)
get_trending_topics
woeid number optional Where On Earth ID (default: 1 = Worldwide)
23424977=USA · 23424950=Spain · 23424900=Mexico
23424747=Argentina · 23424791=Colombia
get_niche_leaders
keyword string required Niche or topic keyword
limit number optional Max accounts (default: 10)
Hosted version (no setup required)
MCPize listing coming soon. Once listed, you'll be able to connect directly without self-hosting or an API key.
Use cases
- Find viral content before writing — search what's already performing well in your niche before you write your next thread or post
- Analyze competitor accounts — understand their engagement rate, best-performing content, and optimal posting times
- Discover trending topics before they peak — catch trends early by monitoring real-time data by country
- Find top creators in any niche — build a list of influencers and voices worth following or collaborating with
- AI-powered content strategy — combine all four tools to let your AI agent build a complete content plan based on real data
Self-hosting on Cloudflare Workers
You can deploy your own instance for free (Cloudflare Workers free tier is generous).
Prerequisites
- Node.js 20+
- Wrangler CLI:
npm install -g wrangler - A Cloudflare account (free)
- A twitterapi.io API key
Deploy
# 1. Clone the repo
git clone https://github.com/fluyeporlaweb/mcp-x-intelligence.git
cd mcp-x-intelligence
# 2. Install dependencies
npm install
# 3. Authenticate with Cloudflare
wrangler login
# 4. Add your API key as a secret
wrangler secret put TWITTERAPI_KEY
# 5. Deploy
wrangler deploy
Your MCP server will be live at https://mcp-x-intelligence.<your-account>.workers.dev.
Local development
Create .dev.vars in the root (already in .gitignore):
TWITTERAPI_KEY=your_key_here
Then run:
npm run dev
GitHub Actions CI/CD
Push to main auto-deploys via GitHub Actions. Add these secrets to your repository:
| Secret | Description |
|---|---|
CLOUDFLARE_API_TOKEN |
Cloudflare API token with Workers edit permission |
CLOUDFLARE_ACCOUNT_ID |
Your Cloudflare account ID |
TWITTERAPI_KEY |
Your twitterapi.io API key |
BYOK (Bring Your Own Key)
Every request can include an x-twitterapi-key header. If present, it overrides the server's configured key. This allows:
- Personal use — deploy once, use with your own key
- Multi-tenant — each user supplies their own key
curl -X POST https://mcp-x-intelligence.<account>.workers.dev \
-H "Content-Type: application/json" \
-H "x-twitterapi-key: tk_YOUR_KEY" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
License
MIT — do whatever you want with it.
Built by @fluyeporlaweb
If this saves you time, follow me on X. I share tools, AI workflows, and content strategy.
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。