Link

Provides automated web content extraction and AI-driven memory management for Cursor projects.

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "lijianye521-link-mcp": {
      "command": "npx",
      "args": [
        "link-mcp2"
      ]
    }
  }
}

Link MCP is an MCP server that automates intelligent web content extraction and conversation memory management for Cursor IDE. It enables structured web docs, component and API extraction, and stored, shareable memories of your technical discussions to improve collaboration and reuse within your projects.

How to use

You use Link MCP with your MCP-enabled client to fetch structured web content and save conversation memories. Start by configuring an MCP server entry in your client, then execute the available tools to fetch documentation or save discussions for future reference.

How to install

Prerequisites: you need Node.js and npm or npx available on your command line.

Option 1: NPX direct usage (recommended) Pull the MCP server via NPX and configure your client to use it.

Option 2: Install via npm then configure your client to reference the local package.

Additional configuration and usage notes

Two MCP server connection options are shown for this setup. Use the one that matches your preferred workflow.

Available tools

fetch_link_documentation

Fetches structured content from a target web page, including page title, components, API interfaces, code blocks, and related links.

save_cursor_memory

Automatically summarize and save the current conversation as a structured Markdown document in the project’s .cursor directory.