Twitter Automation — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Twitter Automation (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Model Context Protocol (MCP) server that enables Claude to automate Twitter posting with AI-generated images and thread support.
npm install -g twitter-automation-mcpTwitter API Keys: Follow this guide to generate your Twitter API keys and tokens: 👉 [Generate Twitter API Keys & Tokens](https://www.ryancarmody.dev/blog/generate-twitter-api-keys-and-tokens)
Google AI API Key: Get your key from Google AI Studio
Add to your Claude Desktop MCP config:
Option A: Using NPM Package (Recommended)
{
"mcpServers": {
"twitter-automation": {
"command": "npx",
"args": ["twitter-automation-mcp"],
"env": {
"TWITTER_API_KEY": "your_api_key",
"TWITTER_API_SECRET": "your_api_secret",
"TWITTER_ACCESS_TOKEN": "your_access_token",
"TWITTER_ACCESS_TOKEN_SECRET": "your_access_token_secret",
"GOOGLE_AI_API_KEY": "your_google_ai_key"
}
}
}
}Option B: Using Local Installation
{
"mcpServers": {
"twitter-automation": {
"command": "node",
"args": ["path/to/twitter-automation/dist/index.js"],
"env": {
"TWITTER_API_KEY": "your_api_key",
"TWITTER_API_SECRET": "your_api_secret",
"TWITTER_ACCESS_TOKEN": "your_access_token",
"TWITTER_ACCESS_TOKEN_SECRET": "your_access_token_secret",
"GOOGLE_AI_API_KEY": "your_google_ai_key"
}
}
}
}Restart Claude Desktop to load the MCP server.
Post this tweet: "Hello world! 👋 #FirstTweet"Generate an image of a robot coding, then post: "AI is the future! 🤖💻"Add this image https://example.com/image.jpg then post: "Check this out!"Post this tweet: "Here's what I learned about AI 🧵"
With thread: ["First insight about machine learning", "Second point about neural networks"]Generate an image "AI brain" for the main tweet
Add URL image https://example.com/chart.jpg for thread tweet 1
Then post the threadThe server provides clear error messages:
"403 Forbidden" errors: Ensure your Twitter app has Read & Write permissions and regenerate access tokens after changing permissions.
"Image upload failed": Check that your images are valid PNG/JPG files under 5MB.
"Content too long": Each tweet must be under 275 characters. Split long content into thread tweets.
Want to deploy this MCP server or run it in a container?
👉 See [DEPLOYMENT.md](DEPLOYMENT.md) for deployment options:
npx (recommended)MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.