Skip to main content
Glama
ShipPost MCP

ShipPost MCP

by RyanKramer

ShipPost MCP — Twitter/X tools for AI agents

Give any AI agent (Claude Code, Cursor, Windsurf, etc.) the ability to read, write, and engage on Twitter/X.

Quick Start

Claude Code

Add to your ~/.claude/settings.json:

{
  "mcpServers": {
    "twitter": {
      "command": "shippost-mcp",
      "env": {
        "TWITTER_ACCESS_TOKEN": "your-access-token",
        "TWITTER_REFRESH_TOKEN": "your-refresh-token",
        "TWITTER_CLIENT_ID": "your-client-id"
      }
    }
  }
}

Install from PyPI

pip install shippost-mcp

Related MCP server: TwitterAPI.io MCP Server

Free Tools

Tool

Description

get_my_profile

Get your Twitter profile

get_timeline

Read your home timeline

get_mentions

Get tweets mentioning you

get_user_profile

Look up any user's profile

get_tweet

Get a specific tweet by ID

search_tweets

Search recent tweets

post_tweet

Post a tweet

reply_to_tweet

Reply to a tweet

like_tweet

Like a tweet

retweet

Retweet a tweet

follow_user

Follow a user

Paid AI Tools (requires ShipPost API key)

Tool

Description

find_opportunities

AI scans your timeline for the best tweets to reply to

draft_reply

AI drafts a reply in your voice

draft_tweet

AI drafts an original tweet

draft_thread

AI drafts a full thread

analyze_account

AI analyzes any Twitter account

get_performance

AI-powered engagement analytics

Get your API key at shippost.ai

Configuration

Env Var

Required

Description

TWITTER_ACCESS_TOKEN

Yes

OAuth 2.0 access token

TWITTER_REFRESH_TOKEN

Recommended

For automatic token renewal

TWITTER_CLIENT_ID

For refresh

Your Twitter app's client ID

SHIPPOST_API_KEY

For AI features

Get at shippost.ai

License

MIT

Available Tools

17 tools
analyze_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

    A3.6/5.0

    Scored across 17 tools

    Disambiguation4/5

    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.

    Naming Consistency4/5

    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.

    Tool Count4/5

    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).

    Completeness4/5

    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.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables LLM agents to interact with Twitter (X) for searching tweets, posting content with images, analyzing engagement, and extracting topics using the Twitter API.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides AI agents and coding assistants with Twitter data access including tweets, user profiles, followers, and search functionality.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to interact with X (Twitter) API v2 for posting tweets, searching, liking, retweeting, and more through natural language.
      23 PyPI
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to fully automate X/Twitter interactions including searching, posting, engaging, and managing multiple accounts without paid API keys.
      MIT