@checkra1neth/xbird
AUse when the user asks to tweet, post threads, read tweets, search Twitter/X, check mentions, manage engagement (like/retweet/bookmark), lists, communities, or update profile. Triggers: twitter, tweet, post, thread, timeline, mentions, followers, bookmark.
Install
agr install @checkra1neth/xbird --target claudeWrites 3 files into .claude/skills/, pinned to git-96c7325f.
- .claude/skills/xbird/LICENSE
- .claude/skills/xbird/README.md
- .claude/skills/xbird/SKILL.md
Document
name: xbird description: "Use when the user asks to tweet, post threads, read tweets, search Twitter/X, check mentions, manage engagement (like/retweet/bookmark), lists, communities, or update profile. Triggers: twitter, tweet, post, thread, timeline, mentions, followers, bookmark."
xbird — Twitter/X for AI Agents
247 MCP tools for Twitter/X with x402 micropayments. Runs locally from residential IP.
Zero config — auto-detects your browser session and generates a wallet. No API keys, no developer account.
When to Use
- Running inside Claude Code, Cursor, or Windsurf
- Need direct MCP tool access to Twitter/X
- Local execution from your own IP
Don't use when: Building backend services or autonomous agents (use REST x402 instead), or operating on Virtuals marketplace (use ACP instead).
Setup
claude mcp add xbird -- npx @checkra1n/xbird
That's it. xbird auto-detects your Twitter session from Chrome, Firefox, Edge, or Safari. A payment wallet is generated automatically on first run.
Full tool list: see tools.md.
Common Workflows
Post tweet with image: upload_media (get mediaId) → post_tweet with mediaIds: ["<id>"]
Get someone's tweets: get_user (get numeric userId) → get_user_tweets with userId
Search and engage: search_tweets with query → like_tweet or retweet results
Update profile: update_profile_image + update_profile with new bio
Quick Reference
Handles: work with or without @ prefix
Pagination: list/search use count (default 20, max 100)
Media: always upload first, then attach mediaId to tweet
Billing: resource × count — post_read $0.0025 | user_read $0.005 | owned_read $0.001
post_create $0.0075 | interaction_create $0.0075 | content_create $0.005
Common Mistakes
| Mistake | Fix |
|---|---|
| Using handle for bulk tools | get_user_tweets, get_followers, etc. need numeric userId. Call get_user first. |
| Posting thread with 1 tweet | post_thread requires minimum 2 tweets. Use post_tweet for single tweet. |
| Media not attached | Upload returns mediaId — must pass it in mediaIds array to post_tweet. |
| Rate limit error | Twitter rate limit. Wait 1-2 minutes, retry. |
| Cookies not detected | Login to x.com in any browser. xbird auto-detects Chrome, Firefox, Edge, Safari. |
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-96c7325f3c0b2026-07-31