
opentwitter-mcp-server
Twitter/X MCP server for fetching user profiles, tweets, follower events, and KOL tracking via AI assistants
- Installs
- 212
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/mcp-skills --skill opentwitter-mcp-server- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads opentwitter-mcp-server automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
opentwitter-mcp-server
Skill by ara.so — MCP Skills collection.
Overview
The opentwitter-mcp is an MCP (Model Context Protocol) server that provides AI assistants with Twitter/X data access capabilities. It enables fetching user profiles, searching tweets, monitoring follower events, tracking deleted tweets, and managing watch lists for KOL (Key Opinion Leader) accounts.
The server connects to the 6551.io API service and exposes 13 tools for Twitter data operations.
Installation
Prerequisites
- Get your API token from https://6551.io/mcp
- Clone or download the repository
- Have
uvpackage manager installed
Quick Install (Claude Code)
claude mcp add twitter \
-e TWITTER_TOKEN=$TWITTER_TOKEN \
-- uv --directory /path/to/twitter-mcp run twitter-mcp
Manual Configuration
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"twitter": {
"command": "uv",
"args": ["--directory", "/path/to/twitter-mcp", "run", "twitter-mcp"],
"env": {
"TWITTER_TOKEN": "${TWITTER_TOKEN}"
}
}
}
}
Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"twitter": {
"command": "uv",
"args": ["--directory", "/path/to/twitter-mcp", "run", "twitter-mcp"],
"env": {
"TWITTER_TOKEN": "${TWITTER_TOKEN}"
}
}
}
}
Continue.dev (~/.continue/config.yaml):
mcpServers:
- name: twitter
command: uv
args:
- --directory
- /path/to/twitter-mcp
- run
- twitter-mcp
env:
TWITTER_TOKEN: ${TWITTER_TOKEN}
Environment Variables
| Variable | Required | Description |
|---|---|---|
TWITTER_TOKEN | Yes | Bearer token from 6551.io |
TWITTER_API_BASE | No | Override API URL (default: https://ai.6551.io) |
TWITTER_MAX_ROWS | No | Max results per query (default: 100) |
Alternative: Create config.json in project root:
{
"api_base_url": "https://ai.6551.io",
"api_token": "your-token-here",
"max_rows": 100
}
Available Tools
User Profile Tools
get_twitter_user - Get user by username
# Example use from AI assistant:
# "Show me @elonmusk's profile"
{
"username": "elonmusk"
}
get_twitter_user_by_id - Get user by numeric ID
{
"user_id": "44196397"
}
Tweet Retrieval Tools
get_twitter_user_tweets - Get recent tweets from a user
# "What did @VitalikButerin tweet recently"
{
"username": "VitalikButerin",
"count": 20
}
get_twitter_tweet_by_id - Get specific tweet with nested replies/quotes
{
"tweet_id": "1234567890"
}
get_twitter_article_by_id - Get Twitter article/long-form content
{
"article_id": "1234567890"
}
Search Tools
search_twitter - Basic keyword search
# "Search Bitcoin related tweets"
{
"query": "Bitcoin",
"count": 50
}
search_twitter_advanced - Advanced search with filters
# "Popular tweets about ETH with 1000+ likes"
{
"query": "ETH",
"min_likes": 1000,
"min_retweets": 100,
"language": "en",
"count": 30
}
Available filters:
min_likes,max_likesmin_retweets,max_retweetsmin_replies,max_replieslanguage(ISO code: en, ja, etc.)since,until(dates)verified_only(boolean)
Engagement Tools
get_twitter_quote_tweets_by_id - Get tweets quoting a specific tweet
# "Who quoted this tweet"
{
"tweet_id": "1234567890",
"count": 50
}
get_twitter_retweet_users_by_id - Get users who retweeted
# "Who retweeted this tweet"
{
"tweet_id": "1234567890",
"count": 100
}
Monitoring Tools
get_twitter_watch - List all monitored accounts
# "Show my Twitter watch list"
{}
add_twitter_watch - Add account to monitoring
# "Monitor @elonmusk with follower tracking"
{
"username": "elonmusk",
"event_types": ["NEW_FOLLOWER", "NEW_UNFOLLOWER", "NEW_TWEET"],
"remark": "Tesla CEO",
"ca": "0x1234..." # Optional contract address
}
Event types:
NEW_TWEET- New tweetsNEW_TWEET_REPLY- RepliesNEW_TWEET_QUOTE- Quote tweetsNEW_RETWEET- RetweetsNEW_FOLLOWER- New followersNEW_UNFOLLOWER- UnfollowersDELETE- Deleted tweetsUPDATE_NAME- Username changesUPDATE_DESCRIPTION- Bio updatesUPDATE_AVATAR- Profile picture changesUPDATE_BANNER- Banner changesCA- Tweets with contract addresses
delete_twitter_watch - Remove from monitoring
{
"username": "elonmusk"
}
Event Tracking Tools
get_twitter_follower_events - Get follower/unfollower events
# "Who followed @elonmusk recently"
{
"username": "elonmusk",
"event_type": "NEW_FOLLOWER",
"count": 50
}
get_twitter_deleted_tweets - Get deleted tweets
# "What tweets did @elonmusk delete"
{
"username": "elonmusk",
"count": 20
}
get_twitter_kol_followers - Get KOL (influential) followers
# "Which KOLs follow @elonmusk"
{
"username": "elonmusk",
"count": 100
}
Data Structures
User Object
{
"userId": "44196397",
"screenName": "elonmusk",
"name": "Elon Musk",
"description": "Bio text...",
"followersCount": 170000000,
"friendsCount": 500,
"statusesCount": 30000,
"verified": true,
"profileImageUrl": "https://...",
"profileBannerUrl": "https://...",
"createdAt": "2009-06-02T20:12:29Z"
}
Tweet Object
{
"id": "1234567890",
"text": "Tweet content...",
"createdAt": "2024-02-20T12:00:00Z",
"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://t.co/...",
"expandedUrl": "https://example.com",
"displayUrl": "example.com"
}
],
"mentions": [
{
"username": "VitalikButerin",
"name": "Vitalik Buterin"
}
]
}
WebSocket Real-time Subscriptions
Connect to wss://ai.6551.io/open/twitter_wss?token=YOUR_TOKEN for real-time events.
Subscribe
{
"jsonrpc": "2.0",
"id": 1,
"method": "twitter.subscribe"
}
Event Notification
{
"jsonrpc": "2.0",
"method": "twitter.event",
"params": {
"id": 123456,
"twAccount": "elonmusk",
"twUserName": "Elon Musk",
"profileUrl": "https://twitter.com/elonmusk",
"eventType": "NEW_TWEET",
"content": { /* tweet object */ },
"ca": "0x1234...",
"remark": "Custom note",
"createdAt": "2026-03-06T10:00:00Z"
}
}
Unsubscribe
{
"jsonrpc": "2.0",
"id": 2,
"method": "twitter.unsubscribe"
}
Common Patterns
Search with Filters
# High-engagement tweets in specific timeframe
search_twitter_advanced(
query="AI",
min_likes=1000,
min_retweets=500,
since="2024-01-01",
until="2024-12-31",
verified_only=True,
language="en"
)
Monitor Multiple Accounts
# Add multiple KOLs to watch list
for username in ["elonmusk", "VitalikButerin", "naval"]:
add_twitter_watch(
username=username,
event_types=["NEW_TWEET", "NEW_FOLLOWER"],
remark=f"Tracking {username}"
)
Track Engagement
# Get full engagement picture for a tweet
tweet = get_twitter_tweet_by_id(tweet_id="1234567890")
quotes = get_twitter_quote_tweets_by_id(tweet_id="1234567890")
retweet_users = get_twitter_retweet_users_by_id(tweet_id="1234567890")
Follower Analysis
# Compare followers vs KOL followers
all_followers = get_twitter_follower_events(
username="elonmusk",
event_type="NEW_FOLLOWER"
)
kol_followers = get_twitter_kol_followers(username="elonmusk")
Development
Run Locally
cd /path/to/twitter-mcp
uv sync
export TWITTER_TOKEN=your-token
uv run twitter-mcp
Debug with MCP Inspector
npx @modelcontextprotocol/inspector \
uv --directory /path/to/twitter-mcp run twitter-mcp
Project Structure
src/twitter_mcp/
├── server.py # Entry point
├── app.py # FastMCP instance
├── config.py # Config loader
├── api_client.py # HTTP client
└── tools.py # Tool implementations
Troubleshooting
Authentication Errors
- Verify
TWITTER_TOKENis set correctly - Check token validity at https://6551.io/mcp
- Ensure no extra whitespace in token value
Rate Limiting
- Default
max_rowsis 100; reduce if hitting limits - Space out requests when monitoring multiple accounts
Connection Issues
- Verify
TWITTER_API_BASEif using custom endpoint - Check firewall/proxy settings for
ai.6551.ioaccess - For WebSocket: ensure WSS protocol is allowed
Empty Results
- Username lookup is case-insensitive but must be exact
- Some accounts may have restricted data access
- Recent tweets may take moments to appear in search
Tool Not Found
- Restart your AI client after config changes
- Verify
uvis in PATH - Check project path is absolute, not relative
Common Use Cases
Content Research: Search tweets with advanced filters to find trending topics, viral content, or specific conversations.
Influencer Monitoring: Track follower growth, engagement patterns, and deleted tweets for transparency.
Community Management: Monitor mentions, replies, and engagement on your own tweets or brand accounts.
Competitive Analysis: Track competitors' follower changes, KOL supporters, and content strategies.
Event Tracking: Set up watches for breaking news, product launches, or community events via real-time WebSocket feeds.
FAQ
What does the opentwitter-mcp-server skill do?
Twitter/X MCP server for fetching user profiles, tweets, follower events, and KOL tracking via AI assistants
How do I install opentwitter-mcp-server?
Run npx skills add https://github.com/reason-machines/mcp-skills --skill opentwitter-mcp-server in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/opentwitter-mcp-server/ (personal) or .claude/skills/opentwitter-mcp-server/ (project).
Which AI agents can use opentwitter-mcp-server?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is opentwitter-mcp-server safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains opentwitter-mcp-server?
It is published by reason-machines in reason-machines/mcp-skills. It has 212 recorded installs.
More from reason-machines/mcp-skills
codebase-memory-mcp-intelligence
reason-machines/mcp-skills
High-performance code intelligence MCP server that indexes codebases into knowledge graphs for structural queries, call traces, and architecture analysis
playwright-mcp-server
reason-machines/mcp-skills
Browser automation MCP server using Playwright's accessibility tree for LLM-friendly web interaction
tradingview-mcp-assistant
reason-machines/mcp-skills
AI-assisted TradingView chart analysis and automation via Chrome DevTools Protocol for Claude Code
lanhu-mcp-collaboration
reason-machines/mcp-skills
Open the skill to read its SKILL.md instructions.
chrome-devtools-mcp-automation
reason-machines/mcp-skills
Expert guidance for Chrome DevTools MCP server - browser automation, debugging, and performance analysis for AI agents
github-mcp-server
reason-machines/mcp-skills
Open the skill to read its SKILL.md instructions.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available