x-ai-mcp
An MCP server that integrates X (Twitter) API access with Grok-powered intelligence for real-time social media analysis and account management. It provides tools for reading and writing tweets, managing direct messages, and generating AI-powered topic summaries or daily briefings.
README
x-ai-mcp
X (Twitter) MCP server with Grok-powered intelligence. Personal account access + AI analysis in one package.
20 tools: 16 X API tools for reading/writing + 4 Grok intelligence tools for real-time analysis.
Setup
1. Install
git clone https://github.com/olivier-motium/x-ai-mcp.git
cd x-ai-mcp
python -m venv .venv && source .venv/bin/activate
pip install -e .
2. Configure
Copy .env.example to .env and fill in:
# Required — X API bearer token (read-only operations)
X_BEARER_TOKEN=your_bearer_token
# Required — your X user ID
X_USER_ID=your_user_id
# Optional — OAuth for write ops (posting, DMs)
# Run: python scripts/auth_flow.py
X_CLIENT_ID=your_client_id
# Optional — xAI key for intelligence tools
XAI_API_KEY=your_xai_key
3. Get OAuth tokens (for write operations)
python scripts/auth_flow.py
Opens browser, authorizes your account, saves token.json. Tokens auto-refresh.
4. Add to Claude Code
claude mcp add x-ai \
-e X_BEARER_TOKEN=xxx \
-e X_USER_ID=xxx \
-e XAI_API_KEY=xxx \
-- python -m src.server
Tools
X API — Timeline & Tweets
| Tool | Description |
|---|---|
x_home_timeline |
Your home timeline |
x_user_tweets |
A user's recent tweets |
x_get_tweet |
Get a specific tweet |
x_post_tweet |
Post a tweet (OAuth) |
x_delete_tweet |
Delete your tweet (OAuth) |
x_search_tweets |
Search recent tweets (7 days) |
X API — DMs
| Tool | Description |
|---|---|
x_list_dms |
Recent DM messages |
x_read_dm |
Read a DM conversation |
x_send_dm |
Send a DM (OAuth) |
X API — Social
| Tool | Description |
|---|---|
x_bookmarks |
Your bookmarked tweets |
x_liked_tweets |
Liked tweets (you or others) |
x_like_tweet |
Like a tweet (OAuth) |
x_user_info |
User profile details |
x_followers |
List followers |
x_following |
List following |
Intelligence — Grok-powered
| Tool | Description |
|---|---|
x_analyze_topic |
Real-time analysis of any topic on X |
x_daily_digest |
AI-powered daily briefing |
x_summarize_thread |
Summarize a tweet thread |
x_analyze_account |
Deep analysis of any X account |
Daily Digest (standalone)
# Default (AI/tech focus)
python scripts/daily_digest.py
# Custom focus
python scripts/daily_digest.py --focus "crypto markets"
# Save to file
python scripts/daily_digest.py --focus "AI agents" --output digest.md
Cron it for daily briefings:
0 9 * * * cd /path/to/x-ai-mcp && .venv/bin/python scripts/daily_digest.py >> ~/digests.log
Architecture
Bearer Token (read) ──┐
OAuth 2.0 PKCE (r/w) ─┤──→ X API v2 ──→ 16 MCP tools
│
xAI API Key ───────────┤──→ Grok (x_search + chat) ──→ 4 intelligence tools
│
Logfire (optional) ────┘──→ Observability dashboard
- X client: async httpx, auto rate-limit retry, OAuth token refresh
- Grok client: Chat Completions API for analysis, Responses API with x_search for real-time X data
- Output: Plain text, never raw JSON. Tweets formatted as
[date time] @user: text (metrics)
License
MIT
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。