How to Use the URL Metadata Scraper MCP in Cursor

Q: How does the URL Metadata Scraper integrate with Cursor's Agent mode?

The scrapeurl tool allows the AI agent to call metadata scraping functions and inject the real, structured data directly into your code. It uses this live context instantly as you write.

Q: Does the URL Metadata Scraper require special setup for Cursor's project scope?

You add it by updating your .cursor/mcp.json file in the project root or globally. Once configured, Agent mode automatically sees and can use the scrapeurl tool.

Q: If I'm writing documentation that contains links, should I use the URL Metadata Scraper?

You absolutely should. Use scrapeurl to get clean metadata for those links before you commit them. It ensures your internal docs look good when shared externally.

Get instant link metadata right in Cursor's Agent mode.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect URL Metadata Scraper MCP to Cursor

Create your Vinkius account to connect URL Metadata Scraper to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup URL Metadata Scraper with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject live SEO context into code

The `scrape_url` tool extracts OpenGraph and SEO data, giving you title, description, and image details. When the AI calls this tool in Agent mode, it injects that real API response directly where your cursor is sitting. You don't get mock stubs; you get actual metadata responses for live context while coding.

Validate external links without leaving Cursor

Before you commit a link to your code, run `scrape_url` against the target URL. The tool quickly gives you clean OpenGraph data—the title and description that will show up when someone shares it. This means you can validate marketing copy or documentation links right in the middle of writing functions.

Automate metadata fetching via Agent mode

Agent mode lets the AI decide when to call `scrape_url`. You just prompt it with a task, and if that task requires link validation, the agent fetches the structured Title, Description, and Image data. It handles the tool invocation and uses the results in your code generation process automatically.

Setup guide

Set up URL Metadata Scraper MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the URL Metadata Scraper MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent URL Metadata Scraper transactions." If the MCP tools are loaded correctly, Cursor will call the URL Metadata Scraper tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "url-metadata-scraper-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cheerio Scraper. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect URL Metadata Scraper now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about URL Metadata Scraper MCP in Cursor

The `scrape_url` tool allows the AI agent to call metadata scraping functions and inject the real, structured data directly into your code. It uses this live context instantly as you write.

Yes. You can prompt the agent to validate a specific URL using `scrape_url`. The resulting OpenGraph metadata helps confirm how that link will appear when shared.

You add it by updating your `.cursor/mcp.json` file in the project root or globally. Once configured, Agent mode automatically sees and can use the `scrape_url` tool.

You absolutely should. Use `scrape_url` to get clean metadata for those links before you commit them. It ensures your internal docs look good when shared externally.

This MCP Server only touches public-facing, structural data from a given URL. Specifically, it reads OpenGraph and standard SEO metadata like Title, Description, and Image paths. It doesn't access user accounts or private content.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript