Opentwitter

If you need to pull Twitter data into Claude workflows, this skill wraps the 6551 API with endpoints for user profiles, tweet searches, follower tracking, and some interesting monitoring features like deleted tweets and KOL follower lists. The search filters are solid: you can narrow by hashtags, engagement thresholds, date ranges, and language. The follower events endpoint lets you track who's following or unfollowing accounts over time, which is useful for social monitoring. You'll need a Bearer token from 6551.io, and the skill uses curl under the hood. It's practical if you're building social listening tools, doing competitor analysis, or just need Twitter data without dealing with X's official API rate limits and authentication complexity.

skills.sh installs: 2K
GitHub stars: 1.4K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add 6551team/opentwitter-mcp --skill opentwitter --agent claude-code

Installs into .claude/skills of the current project.

Files

Twitter/X Data Skill

Query Twitter/X data from the 6551 platform REST API. All endpoints require a Bearer token via $OPENNEWS_TOKEN.

Get your token: http://app.newsliquid.com/mcp

Base URL: https://ai.6551.io

Authentication

All requests require the header:

Authorization: Bearer $OPENNEWS_TOKEN

Meme Evidence Operations

Get Meme Token Evidence

Get the initial thesis and callout evidence for a meme token from the fomo/pump feeds.

curl -s -X POST "https://ai.6551.io/open/meme/token-evidence" \
  -H "Authorization: Bearer $OPENNEWS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"coin": "GADj8JQ8iQLQD5S6ScvncJWmGs7PkwHnXsBrEUns6ue5", "limit": 100}'

Parameters: coin, kind, platform, handle, user, since, and limit. The default kind is thesis,callout; limit is capped at 1000.