⭐ 点我直达右上角点亮星星 | Star this Project
Turn raw URLs into viral hits. Because manually writing posts is so 2025. 将枯燥的链接化为爆款。毕竟，手动写文案已经是 2025 年的老古董了。
ViralTransformer is a high-performance MCP server that turns Claude into a 24/7 social media growth hacker. It doesn't just scrape; it thinks, analyzes, and drafts.
ViralTransformer 是一款高性能 MCP 服务器。它不仅仅是抓取网页，更是将 Claude 变成了一个 24/7 全天候在线的自媒体增长黑客。
Feature | Description |
The "Remake" Command | Give Claude a URL and say "remake this"一键洗稿：丢给 Claude 一个链接，直接收获商业深度稿与情绪爆款稿 |
Dual-Version Output | Get "Deep Insight" for LinkedIn and "High-Energy" for X/Social双重输出：同步生成 LinkedIn 深度观察与 X/小红书情绪爆款 |
Local Drafts | Auto-saves every genius idea to |
Related MCP server: MCP Google Maps
Every ⭐ unlocks a new creative capability.每一颗 ⭐，都是一次 AI 玩法的底层进化
Stars | Achievement |
⭐50 | The Roast Master — AI rewrites news with extreme sarcasm 毒舌教主：开启“键盘侠”模式，让 AI 用最阴阳怪气的口吻重写新闻。 |
⭐188 | Cyberpunk 2077 — Tech-noir storytelling 赛博大饼：把平凡的科技更新，改写成充满霓虹灯、义体、反乌托邦色彩的科幻文案。 |
⭐300 | The Abstract Master — Post-modern "Madness" style 抽象大师：解锁“互联网抽象话”。废话文学、发疯文学，怎么好玩怎么来。 |
⭐520 | "Blind Date" Profile — News as a high-end date bio 高端相亲模式：把枯燥财报改写成“年入百万、海归精英、热爱滑雪”的凡尔赛相亲文案。 |
⭐888 | "The Secret Agent" — Auto-monitor competitors 赛博间谍：发布自动监控对手动态并生成“回击文案”的保姆级自动化教程。 |
FastMCP: High-performance Python framework for MCP.
Httpx: Async-first engine for rapid content retrieval.
BeautifulSoup4: Robust HTML parsing.
Pydantic: Ensuring strict type safety and structured data outputs.
Python 3.10+
uv (Recommended for dependency management)
# Clone the repository
git clone https://github.com/BelleKou/mcp-viral-transformer.git
cd mcp-viral-transformer
# Install dependencies (Modern way)
uv pip install -e .
# Or the traditional way
pip install -r requirements.txtTo use this server, you need an Anthropic API Key. Set it in your environment:
ANTHROPIC_API_KEY: Your key from the Anthropic console.
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"viral-transformer": {
"command": "uv",
"args": [
"run",
"--with", "mcp",
"mcp", "run",
"/your/path/to/mcp-viral-transformer/server.py"
]
}
}
}⚠️ Replace the path with your actual local path.
Source: Anthropic's $30B Compute Deal
Generated File: 📄 drafts/anthropic_30b.md
⚡️ THE $30B COMPUTE HEGEMONY: ANTHROPIC X GOOGLE X BROADCOM
🏛️ Version A: Professional Insight
Title: The Death of Asset-Light AI: Anthropic's Vertical Integration Bet
The recent $30B partnership between Anthropic, Google, and Broadcom marks a tectonic shift. We are moving away from "Algorithm Supremacy" toward "Compute Sovereignty."
The Hardware Pivot: Co-designing ASICs with Broadcom to bypass the NVIDIA bottleneck.
Infrastructure Moat: Scaling laws now require a direct relationship with the power grid.
🚀 Version B: High-Energy Viral
Title: $30 BILLION. That's the price of admission for the AGI race. 💸
While everyone is arguing over prompts, Anthropic just bought the building. And the chips. And the power lines.
🔮 UNIQUE ANGLE
AI is shifting from software to a "Digital Utility." In 2026, the leading AI company looks less like Microsoft and more like a combination of TSMC and energy conglomerates.
Source: 36Kr - 吉利沃飞长空 IPO
Generated File: 📄 drafts/sky_economy.md
🚁 11个IPO！"汽车狂人"的最后拼图：低空经济不是梦，是生意。
🏛️ Version A: 深度商业观察
标题：从"二维道路"到"三维空间"：沃飞长空的资本纵横术
沃飞长空启动IPO辅导，标志着"低空经济"已从概念进入资本收割期。这不仅是造飞行汽车，更是对城市空间主权的重构。
🚀 Version B: 情绪爆款文案
标题：别再地面卷了！以后出门打"飞的"，只要10分钟？💸
当年被嘲笑的"疯话"，现在全成了真！天空正式变成"车道"，低空出行的时代来了。卖的不是飞机，是"绕过拥堵的特权"。
🔮 UNIQUE ANGLE
时间主权的阶级化：2026年，阶级分层将体现在"垂直准入权"上。沃飞长空抢占的300米高度，是未来50年城市秩序的终极解释权。
.
├── server.py # Core MCP logic
├── LICENSE # MIT License
├── requirements.txt # Project dependencies
├── drafts/ # Generated markdown posts (Output)
└── README.md # DocumentationLicensed under the MIT License. Open for modification and personal use.
Saves content with a safe filename to the /drafts folder.
| Name | Required | Description | Default |
|---|---|---|---|
| filename | Yes | ||
| content | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'saves content' (implying a write operation) and mentions a 'safe filename', but doesn't clarify permissions, error handling, or what 'safe' entails. This leaves significant gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's action and destination. It's front-loaded with the core purpose and has no wasted words, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has an output schema (which reduces the need to describe return values) but no annotations and 0% schema coverage, the description is minimally adequate. It covers the basic action and location but lacks details on behavior and parameters, making it incomplete for a mutation tool with undocumented inputs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It mentions 'safe filename' and '/drafts folder', which adds some context for the 'filename' parameter, but doesn't explain 'content' or provide details on filename safety rules. This partial compensation is insufficient for the 2 undocumented parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Saves content') and target ('to the /drafts folder'), with the verb 'saves' being specific. However, it doesn't differentiate from the sibling tool 'scrape_article' (which appears unrelated), so it doesn't fully earn a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It mentions saving to '/drafts folder' but doesn't specify use cases, prerequisites, or exclusions, leaving the agent with minimal context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scrapes clean content from a URL, focusing on the main article body.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool scrapes clean content and focuses on the main article body, which hints at behavior like content cleaning and body extraction. However, it lacks details on error handling, rate limits, authentication needs, or what 'clean' entails, leaving significant gaps for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core action and focus. Every word earns its place, with no redundancy or unnecessary elaboration, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has an output schema (which covers return values), no annotations, and a simple input schema, the description is minimally adequate. It specifies the tool's focus on article body content, but for a scraping tool with no behavioral annotations, it could benefit from more context on limitations or expected output format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention the 'url' parameter explicitly, but with only 1 parameter and 0% schema description coverage, it compensates by implying the parameter's purpose through context ('from a URL'). This adds meaning beyond the bare schema, though it doesn't detail format or constraints, keeping it from a perfect score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('scrapes') and resource ('clean content from a URL'), specifying it focuses on the main article body. This distinguishes it from generic scraping tools, though it doesn't explicitly differentiate from the sibling 'save_draft' tool, which appears unrelated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as other scraping methods or tools. It mentions focusing on the main article body, which implies a context for article content extraction, but lacks explicit when/when-not instructions or named alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0save_draftscrape_articleScored across 2 tools
The two tools have completely distinct purposes: save_draft handles local file saving with safe naming, while scrape_article extracts clean content from URLs. There is no overlap in functionality or ambiguity between them.
Both tools follow a consistent verb_noun pattern (save_draft, scrape_article) with clear, descriptive names that align well with their functions. The naming style is uniform and predictable.
With only two tools, the server feels thin and under-scoped for a 'ViralTransformer' purpose, which implies content transformation or viral content handling. This minimal set limits functionality and suggests incomplete coverage of the domain.
The tool set is severely incomplete for a viral content transformation server. It lacks core operations like content generation, editing, publishing, analytics, or social media integration, leaving significant gaps that will hinder agent workflows.
PostHero MCP server — schedule and publish social media posts from any MCP-compatible AI tool
MCP server for QPost — lets AI agents publish video and image posts to YouTube, TikTok, Instagram.
WordPress MCP server: generate SEO posts, AI images, autoblog & WooCommerce on your self-hosted site
Social media MCP server: your Instagram, TikTok, YouTube, LinkedIn and Threads history for your AI.