Twitter MCP Server
This server lets AI assistants access and monitor Twitter/X data through MCP tools.
User profiles: Get user info by username or numeric ID
Tweets: Fetch recent tweets, replies, and retweets from a user
Search: Basic and advanced tweet search with filters (keywords, users, hashtags, likes, retweets, replies, date range, language, sort order)
Engagement: View quotes, retweeters, and KOL followers for a user or tweet
Follower tracking: Retrieve follower/unfollower events, deleted tweets, and real-time WebSocket event subscriptions
Monitoring: Add, list, and delete Twitter users in a watch list with custom notes and group names
Meme token analysis: Get thesis/callout evidence and later statements/buy-sell activity for meme tokens
Articles: Fetch Twitter articles by ID
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Twitter MCP Server find popular tweets about #AI with more than 1000 likes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Quick Install
First, go to http://app.newsliquid.com/mcp to get your API Token.
Claude Code
claude mcp add twitter \
-e OPENNEWS_TOKEN=<your-token> \
-- uv --directory /path/to/twitter-mcp run twitter-mcpReplace
/path/to/twitter-mcpwith your local project path, and<your-token>with your Token.
OpenClaw
export OPENNEWS_TOKEN="<your-token>"
cp -r openclaw-skill/opentwitter ~/.openclaw/skills/Related MCP server: Apex MCP for X Management
Let AI Review & Install For You
Not sure if this MCP is safe? Paste the prompt below to your AI assistant — it will review the source code first, then install if safe:
Copy this prompt and send it to your AI assistant (replace
<project-path>and<your-token>with actual values):
Please review and install the twitter-mcp MCP server for me. The project is at <project-path>.
Steps:
1. Review these files for security:
- src/twitter_mcp/api_client.py — Confirm it only connects to ai.6551.io, no data sent elsewhere
- src/twitter_mcp/config.py — Confirm token is only read from local config.json or env vars, no hardcoded secrets or leaks
- src/twitter_mcp/tools.py — Confirm all tools only perform API queries, no file writes, command execution, or dangerous operations
- pyproject.toml — Confirm dependencies are only mcp, httpx, no suspicious packages
2. Tell me your conclusion: safe / risky / problematic, with specific reasons
3. If safe, run the install (get Token from http://app.newsliquid.com/mcp):
claude mcp add twitter -e OPENNEWS_TOKEN=<your-token> -- uv --directory <project-path> run twitter-mcpWhat Can It Do?
Once connected, just ask your AI assistant:
You say | It does |
"Show @elonmusk's Twitter profile" | Get user profile info |
"What did @VitalikButerin tweet recently" | Get user's recent tweets |
"Search Bitcoin related tweets" | Keyword search |
"Find tweets with #crypto hashtag" | Hashtag search |
"Popular tweets about ETH with 1000+ likes" | Search with engagement filters |
"Monitor @elonmusk with follower tracking and a custom note" | Add user to watch list with options |
"Who quoted this tweet" | Get quote tweets for a tweet |
"Who retweeted this tweet" | Get users who retweeted a tweet |
"Who followed @elonmusk recently" | Get new follower events |
"Who unfollowed @elonmusk" | Get unfollower events |
"What tweets did @elonmusk delete" | Get deleted tweets |
"Which KOLs follow @elonmusk" | Get KOL followers |
"Show the thesis and callout evidence for this meme token" | Get token evidence from fomo/pump feeds |
"Show the later statements and buys/sells for this token" | Get meme activity and trade evidence |
Available Tools
Tool | Description |
| Get user profile by username |
| Get user profile by numeric ID |
| Get recent tweets from a user |
| Search tweets with |
| Advanced search with multiple filters |
| Get follower/unfollower events |
| Get deleted tweets from a user |
| Get KOL (Key Opinion Leader) followers |
| Get thesis and callout evidence for a meme token |
| Get meme token statements and buy/sell evidence |
| Get Twitter article by ID |
| Get tweet by ID with nested reply/quote tweets |
| Get tweets that quote a specific tweet |
| Get users who retweeted a specific tweet |
| Get all Twitter monitoring users |
| Add a Twitter user to monitoring list (with event type options, |
| Delete a Twitter user from monitoring list |
Configuration
Get API Token
Go to http://app.newsliquid.com/mcp to get your API Token.
Set the environment variable:
# macOS / Linux
export OPENNEWS_TOKEN="<your-token>"
# Windows PowerShell
$env:OPENNEWS_TOKEN = "<your-token>"Variable | Required | Description |
| Yes | 6551 API Bearer Token (get from http://app.newsliquid.com/mcp) |
| No | Override REST API URL |
| No | Max results per query (default: 100) |
Also supports config.json in the project root (env vars take precedence):
{
"api_base_url": "https://ai.6551.io",
"api_token": "<your-token>",
"max_rows": 100
}WebSocket Real-time Subscriptions
Endpoint: wss://ai.6551.io/open/twitter_wss?token=YOUR_TOKEN
Subscribe to real-time events from your monitored Twitter accounts.
Heartbeat
To keep the connection alive, the client can send ping, and the server responds with pong.
Subscribe to Twitter Events
{
"jsonrpc": "2.0",
"id": 1,
"method": "twitter.subscribe"
}Response:
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"success": true
}
}Unsubscribe
{
"jsonrpc": "2.0",
"id": 2,
"method": "twitter.unsubscribe"
}Server Push - Twitter Event
When a monitored account has activity, the server pushes:
{
"jsonrpc": "2.0",
"method": "twitter.event",
"params": {
"id": 123456,
"twAccount": "elonmusk",
"twUserName": "Elon Musk",
"profileUrl": "https://twitter.com/elonmusk",
"eventType": "NEW_TWEET",
"content": "...",
"ca": "0x1234...",
"remark": "Custom note",
"createdAt": "2026-03-06T10:00:00Z"
}
}Note: The content field structure varies by event type (see below).
**Event Types and Content Structure**:
#### Tweet Events
- `NEW_TWEET` - New tweet posted
- `NEW_TWEET_REPLY` - New reply tweet
- `NEW_TWEET_QUOTE` - New quote tweet
- `NEW_RETWEET` - Retweeted
- `CA` - Tweet with CA address
Content structure for tweet events:
```json
{
"id": "1234567890",
"text": "Tweet content...",
"createdAt": "2026-03-06T10:00:00Z",
"language": "en",
"retweetCount": 100,
"favoriteCount": 500,
"replyCount": 20,
"quoteCount": 10,
"viewCount": 10000,
"userScreenName": "elonmusk",
"userName": "Elon Musk",
"userIdStr": "44196397",
"userFollowers": 170000000,
"userVerified": true,
"conversationId": "1234567890",
"isReply": false,
"isQuote": false,
"hashtags": ["crypto", "bitcoin"],
"media": [
{
"type": "photo",
"url": "https://...",
"thumbUrl": "https://..."
}
],
"urls": [
{
"url": "https://...",
"expandedUrl": "https://...",
"displayUrl": "example.com"
}
],
"mentions": [
{
"username": "VitalikButerin",
"name": "Vitalik Buterin"
}
]
}Follower Events
NEW_FOLLOWER- This account followed a userNEW_UNFOLLOWER- This account unfollowed a user
Content structure for follower events (array):
[
{
"id": 123,
"twId": 44196397,
"twAccount": "elonmusk",
"twUserName": "Elon Musk",
"twUserLabel": "Verified",
"description": "User bio...",
"profileUrl": "https://...",
"bannerUrl": "https://...",
"followerCount": 170000000,
"friendCount": 500,
"createdAt": "2026-03-06T10:00:00Z"
}
]Profile Update Events
UPDATE_NAME- Username changed (content: new name string)UPDATE_DESCRIPTION- Bio updated (content: new description string)UPDATE_AVATAR- Profile picture changed (content: new avatar URL string)UPDATE_BANNER- Banner image changed (content: new banner URL string)
Other Events
TWEET_TOPPING- Tweet pinnedDELETE- Tweet deletedSYSTEM- System eventTRANSLATE- Tweet translationCA_CREATE- CA token created
Data Structures
Twitter User
{
"userId": "44196397",
"screenName": "elonmusk",
"name": "Elon Musk",
"description": "...",
"followersCount": 170000000,
"friendsCount": 500,
"statusesCount": 30000,
"verified": true
}Tweet
{
"id": "1234567890",
"text": "Tweet content...",
"createdAt": "2024-02-20T12:00:00Z",
"retweetCount": 1000,
"favoriteCount": 5000,
"replyCount": 200,
"userScreenName": "elonmusk",
"hashtags": ["crypto", "bitcoin"],
"urls": [{"url": "https://..."}]
}Meme Feed Item
Meme evidence tools return fomo/pump feed data, including platform, kind,
author, text, createdAt, and (for trades) a trade object. Use
get_meme_token_evidence for the initial thesis/callout view and
get_meme_activity for later statements and buy/sell evidence.
In all configs below, replace
/path/to/twitter-mcpwith your actual local project path, and<your-token>with your Token from http://app.newsliquid.com/mcp.
Claude Desktop
Edit config (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"twitter": {
"command": "uv",
"args": ["--directory", "/path/to/twitter-mcp", "run", "twitter-mcp"],
"env": {
"OPENNEWS_TOKEN": "<your-token>"
}
}
}
}Cursor
~/.cursor/mcp.json or Settings > MCP Servers:
{
"mcpServers": {
"twitter": {
"command": "uv",
"args": ["--directory", "/path/to/twitter-mcp", "run", "twitter-mcp"],
"env": {
"OPENNEWS_TOKEN": "<your-token>"
}
}
}
}Windsurf
~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"twitter": {
"command": "uv",
"args": ["--directory", "/path/to/twitter-mcp", "run", "twitter-mcp"],
"env": {
"OPENNEWS_TOKEN": "<your-token>"
}
}
}
}Cline
VS Code sidebar > Cline > MCP Servers > Configure, edit cline_mcp_settings.json:
{
"mcpServers": {
"twitter": {
"command": "uv",
"args": ["--directory", "/path/to/twitter-mcp", "run", "twitter-mcp"],
"env": {
"OPENNEWS_TOKEN": "<your-token>"
},
"disabled": false,
"autoApprove": []
}
}
}Continue.dev
~/.continue/config.yaml:
mcpServers:
- name: twitter
command: uv
args:
- --directory
- /path/to/twitter-mcp
- run
- twitter-mcp
env:
OPENNEWS_TOKEN: <your-token>Cherry Studio
Settings > MCP Servers > Add > Type stdio: Command uv, Args --directory /path/to/twitter-mcp run twitter-mcp, Env OPENNEWS_TOKEN.
Zed Editor
~/.config/zed/settings.json:
{
"context_servers": {
"twitter": {
"command": {
"path": "uv",
"args": ["--directory", "/path/to/twitter-mcp", "run", "twitter-mcp"],
"env": {
"OPENNEWS_TOKEN": "<your-token>"
}
}
}
}
}Any stdio MCP client
OPENNEWS_TOKEN=<your-token> \
uv --directory /path/to/twitter-mcp run twitter-mcpCompatibility
Client | Install Method | Status |
Claude Code |
| One-liner |
OpenClaw | Copy skill directory | One-liner |
Claude Desktop | JSON config | Supported |
Cursor | JSON config | Supported |
Windsurf | JSON config | Supported |
Cline | JSON config | Supported |
Continue.dev | YAML / JSON | Supported |
Cherry Studio | GUI | Supported |
Zed | JSON config | Supported |
Development
cd /path/to/twitter-mcp
uv sync
uv run twitter-mcp# MCP Inspector
npx @modelcontextprotocol/inspector uv --directory /path/to/twitter-mcp run twitter-mcpProject Structure
├── README.md
├── docs/
│ ├── README_JA.md # 日本語
│ └── README_KO.md # 한국어
├── openclaw-skill/opentwitter/ # OpenClaw Skill
├── pyproject.toml
├── config.json
└── src/twitter_mcp/
├── server.py # Entry point
├── app.py # FastMCP instance
├── config.py # Config loader
├── api_client.py # HTTP client
└── tools.py # 8 toolsLicense
MIT
Available Tools
12 toolsadd_twitter_watchB
Add a Twitter user to monitoring list.
Args: username: Twitter username to monitor (without @).
Inputs: username (required).
delete_twitter_watchC
Delete a Twitter user from monitoring list.
Args: watch_id: The monitoring record ID to delete.
Inputs: watch_id (required).
get_twitter_article_by_idC
Get Twitter article by ID.
Args: article_id: Twitter article ID.
Inputs: article_id (required).
get_twitter_deleted_tweetsB
Get deleted tweets from a Twitter/X user.
Args: username: Twitter username (without @). limit: Maximum tweets to return (default 20, max 100).
Inputs: username (required), limit.
get_twitter_follower_eventsB
Get follower/unfollower events for a Twitter/X user.
Args: username: Twitter username (without @). is_follow: True for new followers, False for unfollowers. limit: Maximum events to return (default 20, max 100).
Inputs: username (required), is_follow, limit.
get_twitter_kol_followersC
Get KOL (Key Opinion Leader) followers for a Twitter/X user.
Returns which influential accounts (KOLs) are following this user.
Args: username: Twitter username (without @).
Inputs: username (required).
get_twitter_userA
Get Twitter/X user profile information by username.
Args: username: Twitter username (without @, e.g. "elonmusk").
Inputs: username (required).
get_twitter_user_by_idB
Get Twitter/X user profile information by user ID.
Args: user_id: Twitter user ID (numeric string).
Inputs: user_id (required).
get_twitter_user_tweetsA
Get recent tweets from a specific Twitter/X user.
Args: username: Twitter username (without @). limit: Maximum tweets to return (default 20, max 100). include_replies: Include reply tweets (default False). include_retweets: Include retweets (default False).
Inputs: username (required), limit, include_replies, include_retweets.
get_twitter_watchB
Get all Twitter monitoring users for the current user.
Returns a list of Twitter accounts being monitored.
Inputs: no named parameters.
search_twitterA
Search Twitter/X for tweets matching criteria.
Args: keywords: Search keywords. from_user: Filter tweets from specific user (without @). hashtag: Filter by hashtag (without #). min_likes: Minimum likes threshold. limit: Maximum tweets to return (default 20, max 100).
Inputs: keywords, from_user, hashtag, min_likes, +1 more.
search_twitter_advancedB
Advanced Twitter/X search with multiple filters.
Args: keywords: Search keywords. from_user: Filter tweets from specific user. to_user: Filter tweets to specific user. mention_user: Filter tweets mentioning specific user. hashtag: Filter by hashtag (without #). exclude_replies: Exclude reply tweets. exclude_retweets: Exclude retweets. min_likes: Minimum likes threshold. min_retweets: Minimum retweets threshold. min_replies: Minimum replies threshold. since_date: Start date (YYYY-MM-DD). until_date: End date (YYYY-MM-DD). lang: Language code (e.g. "en", "zh"). product: Sort by "Top" or "Latest" (default "Top"). limit: Maximum tweets to return (default 20, max 100).
Inputs: keywords, from_user, to_user, mention_user, +11 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Most tools have distinct purposes, but there is some overlap between get_twitter_user and get_twitter_user_by_id (both retrieve user profiles via different identifiers) and between search_twitter and search_twitter_advanced (both search tweets, with the latter being a superset). The descriptions clarify the differences, preventing major confusion.
All tool names follow a consistent snake_case pattern with clear verb_noun structures (e.g., add_twitter_watch, get_twitter_user_tweets, search_twitter_advanced). The naming is predictable and uniform across all 12 tools.
With 12 tools, the server is well-scoped for Twitter/X monitoring and data retrieval. The count is appropriate, covering user management, tweet fetching, search, and monitoring without being overwhelming or insufficient for the domain.
The toolset provides strong coverage for monitoring and retrieving Twitter data, including user profiles, tweets, searches, and follower events. Minor gaps exist, such as no tools for posting tweets or interacting with tweets (e.g., liking, retweeting), but core retrieval and monitoring workflows are well-covered.
Maintenance
Related MCP Connectors
Live X/Twitter data: profiles, tweets, search, followers, lists and trends. 29 read-only tools.
Read-only public X (Twitter) data: profiles, tweets, threads, followers, search. Pay per result.
X (formerly Twitter): X (formerly Twitter) public and private data API for search, posts (Tweets).
Twitter (X) data for agents: profiles, tweets, search, followers, lists. $0.0006 per call.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables interaction with X (formerly Twitter), allowing for posting tweets, searching content, managing accounts, and organizing lists.1119 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables complete management of X (Twitter) accounts through a single API key, supporting functions like getting tweets, searching, generating and posting replies.54 npm2MIT
- AlicenseNot gradedqualityDmaintenanceEnables interaction with X (Twitter) to post tweets, threads, and replies while retrieving tweet metrics and account information. It supports core management tasks like deleting tweets and verifying authentication through the Twitter API.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to access Twitter/X data including user profiles, tweets, search, and follower events via a set of MCP tools.MIT