A set of rules for retrieving and analyzing articles published on X, formerly known as Twitter. It requires using a browser-based article tool because these pages need JavaScript to load their content.

Use it when an agent must fetch or analyze an X article or a matching Twitter article URL.

Simple web requests may return empty or incomplete X articles. These rules direct the agent to the method that can render and read them correctly.

cursorrules — Cursor rule by vibeforge1111

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add rules/vibeforge1111/xmcp/cursorrules

Clone the repo

git clone --depth 1 https://github.com/vibeforge1111/xmcp

Made for: Cursor.

Per session 626 This file is loaded in full into every session.

When invoked 626 The same file — it is already loaded in full.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00626	$0.00626
Opus 5	$0.00313	$0.00313
Sonnet 5	$0.00125	$0.00125
Haiku 4.5	$0.00063	$0.00063

Measured 2d ago against content hash 47db7fea99d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. **NEVER use WebFetch, curl, or requests** - they will return empty/broken content

.cursorrules · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Rules for XMCP

CRITICAL: X/Twitter Article Fetching

When the user asks you to read, fetch, or analyze an X/Twitter article:

ALWAYS use the get_article MCP tool - it uses Playwright to render JavaScript
NEVER use WebFetch, curl, or requests - they will return empty/broken content
X articles require JavaScript rendering - only Playwright works

Correct Pattern

User: "Read this X article: https://x.com/user/status/123"
You: Use mcp__x-twitter__get_article with the URL

Wrong Pattern (DO NOT DO THIS)

User: "Read this X article"
You: WebFetch("https://x.com/...")  # WRONG - will fail
You: requests.get("https://x.com/...")  # WRONG - will fail

Article URLs That Need Playwright

Any URL matching these patterns requires get_article:

https://x.com/*/status/*
https://twitter.com/*/status/*
https://x.com/i/article/*
https://twitter.com/i/article/*

Available MCP Tools

The x-twitter MCP provides these tool categories:

Research (Read-Only)

search_twitter - Search with engagement metrics
search_articles - Find tweets with articles
get_article - Fetch article content (USES PLAYWRIGHT)
get_user_profile, get_user_by_screen_name - User info
get_tweet_details - Tweet info
get_trends - Trending topics

Engagement

favorite_tweet / unfavorite_tweet - Like/unlike
retweet / unretweet - Retweet
bookmark_tweet - Save tweets

Publishing

post_tweet - Post a tweet
create_thread - Post a thread
quote_tweet - Quote tweet
create_poll_tweet - Create poll

Conversations

get_conversation - Get full thread
get_replies - Get replies to a tweet

Permissions

Tools are permission-gated by profile. If a tool fails with "not enabled":

Default profile is researcher (read-only)
Publishing requires creator profile
Social actions require manager profile

When User Mentions Twitter/X

If they want to search: Use search_twitter
If they want to read an article: Use get_article (PLAYWRIGHT)
If they want to see a thread: Use get_conversation
If they want to post: Use post_tweet or create_thread
If they want user info: Use get_user_by_screen_name

Read the full file on GitHub · 73 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 73 lines · 626 tokens per session scan A 47db7fea99d5

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository vibeforge1111/xmcp (18 stars, last pushed 7mo ago), licensed MIT. It adds 626 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation Languages Writing and docs

cursorrules