ShipPost MCP
ShipPost MCP — AI 에이전트를 위한 Twitter/X 도구
모든 AI 에이전트(Claude Code, Cursor, Windsurf 등)가 Twitter/X에서 읽고, 쓰고, 참여할 수 있는 기능을 제공합니다.
빠른 시작
Claude Code
~/.claude/settings.json에 추가하세요:
{
"mcpServers": {
"twitter": {
"command": "shippost-mcp",
"env": {
"TWITTER_ACCESS_TOKEN": "your-access-token",
"TWITTER_REFRESH_TOKEN": "your-refresh-token",
"TWITTER_CLIENT_ID": "your-client-id"
}
}
}
}PyPI에서 설치
pip install shippost-mcpRelated MCP server: TwitterAPI.io MCP Server
무료 도구
도구 | 설명 |
| 내 Twitter 프로필 가져오기 |
| 홈 타임라인 읽기 |
| 나를 언급하는 트윗 가져오기 |
| 모든 사용자의 프로필 조회 |
| ID로 특정 트윗 가져오기 |
| 최근 트윗 검색 |
| 트윗 게시 |
| 트윗에 답글 |
| 트윗 좋아요 |
| 트윗 리트윗 |
| 사용자 팔로우 |
유료 AI 도구 (ShipPost API 키 필요)
도구 | 설명 |
| AI가 타임라인을 스캔하여 답글하기 가장 좋은 트윗을 찾아줍니다 |
| AI가 내 목소리로 답글을 작성합니다 |
| AI가 독창적인 트윗을 작성합니다 |
| AI가 전체 스레드를 작성합니다 |
| AI가 모든 Twitter 계정을 분석합니다 |
| AI 기반 참여도 분석 |
shippost.ai에서 API 키를 받으세요
구성
환경 변수 | 필수 여부 | 설명 |
| 예 | OAuth 2.0 액세스 토큰 |
| 권장 | 자동 토큰 갱신용 |
| 갱신용 | Twitter 앱의 클라이언트 ID |
| AI 기능용 | shippost.ai에서 받기 |
라이선스
MIT
Available Tools
17 toolsanalyze_accountA
Analyze a Twitter account — who they are, what they post about, engagement patterns.
Useful for deciding whether to engage with someone or understanding their audience.
Requires a ShipPost API key (SHIPPOST_API_KEY). Get one at https://shippost.ai
Inputs: username (required). Returns: result
draft_replyA
Draft a reply to a tweet in your voice using AI.
Analyzes the tweet and generates a reply that matches your writing style. Returns a DRAFT — does not post automatically. Use reply_to_tweet() to post.
Requires a ShipPost API key (SHIPPOST_API_KEY). Get one at https://shippost.ai
Inputs: tweet_id (required), tweet_text (required), tweet_author (required). Returns: result
draft_threadA
Draft a tweet thread about a topic in your voice using AI.
Returns DRAFTS — does not post. Review and use post_tweet() for each.
Requires a ShipPost API key (SHIPPOST_API_KEY). Get one at https://shippost.ai
Inputs: topic (required), style, length. Returns: result
draft_tweetA
Draft an original tweet about a topic in your voice using AI.
Returns a DRAFT — does not post automatically. Use post_tweet() to post.
Requires a ShipPost API key (SHIPPOST_API_KEY). Get one at https://shippost.ai
Inputs: topic (required), style. Returns: result
find_opportunitiesA
Scan my timeline and find the best tweets to reply to, scored by relevance.
Uses AI to analyze each tweet and score it on:
Relevance to your niche/expertise
Engagement potential (will a reply get seen?)
Reply opportunity (can you add genuine value?)
Returns scored tweets with suggested reply angles.
Requires a ShipPost API key (SHIPPOST_API_KEY). Get one at https://shippost.ai
Inputs: niche, max_results. Returns: result
follow_userB
Follow a Twitter user.
Inputs: username (required). Returns: result
get_mentionsA
Get recent tweets that mention me.
Returns tweets where other users have @mentioned the authenticated user.
Inputs: max_results. Returns: result
get_my_profileA
Get the authenticated Twitter user's profile — name, bio, follower count, tweet count.
Inputs: no named parameters. Returns: result
get_performanceA
Get engagement analytics on your recent tweets.
Shows which tweets performed best, what's working, and trends.
Requires a ShipPost API key (SHIPPOST_API_KEY). Get one at https://shippost.ai
Inputs: days. Returns: result
get_timelineA
Get recent tweets from my home timeline.
Returns tweets with text, author, engagement metrics, and URLs. Use this to see what's happening in the user's feed.
Inputs: max_results. Returns: result
get_tweetA
Get a specific tweet by its ID.
Returns the full tweet text, author, engagement metrics, and conversation context.
Inputs: tweet_id (required). Returns: result
get_user_profileA
Look up a Twitter user's profile by their username.
Returns their name, bio, follower/following counts, and tweet count.
Inputs: username (required). Returns: result
like_tweetB
Like a tweet.
Inputs: tweet_id (required). Returns: result
post_tweetA
Post a tweet from the authenticated user's account.
The tweet will be posted immediately and publicly visible.
Inputs: text (required). Returns: result
reply_to_tweetA
Reply to a specific tweet.
Posts a public reply to the given tweet from the authenticated user's account.
Inputs: text (required), tweet_id (required). Returns: result
retweetB
Retweet a tweet.
Inputs: tweet_id (required). Returns: result
search_tweetsA
Search recent tweets by keyword or phrase.
Searches the last 7 days of public tweets. Retweets are excluded. Returns tweets with text, author, engagement metrics, and URLs.
Inputs: query (required), max_results. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Most tools are clearly distinct (get_tweet vs get_timeline vs get_mentions), but get_my_profile and get_user_profile could be confused if not for the 'my' vs 'user' distinction. The draft_* tools are distinct from post/reply actions.
Tools follow a consistent verb_noun pattern (get_*, post_*, reply_to_*, like_*, retweet, follow_*, draft_*, analyze_*, find_*). Minor deviation: 'retweet' lacks an underscore but is still clear and consistent with the action.
17 tools is slightly above the ideal range but appropriate for a Twitter client with both standard actions and AI-assisted features. Each tool serves a distinct purpose, though some could be consolidated (e.g., draft_tweet and draft_thread).
Covers core Twitter operations (read, post, reply, like, retweet, follow) plus analytics and AI drafting. Missing delete_tweet, unfollow, and block/mute, but the main engagement workflow is complete. The AI features add value beyond basic CRUD.
Maintenance
Related MCP Connectors
Publish and schedule tweets and threads on X (Twitter) from your AI assistant.
X (formerly Twitter) posts, profiles, and search for AI agents. Free key, self-minted, no signup.
Twitter (X) API alternative for AI agents: tweet search, profiles, followers. $0.0002 per result.
Your agent posts, schedules, queues and threads posts on X, with a human approval queue.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables LLM agents to interact with Twitter (X) for searching tweets, posting content with images, analyzing engagement, and extracting topics using the Twitter API.-
- AlicenseNot gradedqualityDmaintenanceProvides AI agents and coding assistants with Twitter data access including tweets, user profiles, followers, and search functionality.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with X (Twitter) API v2 for posting tweets, searching, liking, retweeting, and more through natural language.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to fully automate X/Twitter interactions including searching, posting, engaging, and managing multiple accounts without paid API keys.MIT