MCP Bookmark Server

Saves URLs with metadata and enables AI-powered semantic search across bookmarks for quick, contextual access.

javascript

0

GitHub Stars

javascript

Language

4 months ago

First Indexed

2 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": {
    "pree-dew-mcp-bookmark": {
      "command": "/usr/local/bin/uvx",
      "args": [
        "--from",
        "git+https://github.com/pree-dew/mcp-bookmark.git",
        "mcp-bookmark-server"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run the MCP Bookmark Server to store and semantically search your bookmarks using AI-assisted capabilities. It integrates with your MCP ecosystem to save URLs with metadata, perform smart searches across titles and descriptions, and categorize items using AI-powered reasoning, all accessible from multiple MCP-compatible clients.

How to use

Use any MCP client that supports standard MCP commands to interact with the Bookmark Server. You can save bookmarks by providing a URL and optional title and description, and you can search your collection with natural language queries. Typical workflows include saving a development resource with a descriptive title, then later querying for bookmarks related to a topic like machine learning or React tutorials. The server handles semantic search across titles and descriptions and leverages AI for smarter categorization and retrieval.

How to install

Prerequisites you need before installation: Python 3.11 or newer, an OpenAI API key, and a working internet connection to access dependencies and the GitHub repository.

Install the MCP Bookmark Server package from PyPI using Python’s package manager.

pip install mcp-bookmark-server

Configuration for MCP Hosts

Configure each MCP host to connect to the Bookmark Server by providing the uvx command, the required arguments to pull the MCP package from GitHub, and your OpenAI API key. The following examples show the standard configuration snippet you would place in the host’s MCP config.

{
  "mcpServers": {
    "bookmark": {
      "command": "/usr/local/bin/uvx",
      "args": [
        "--from",
        "git+https://github.com/pree-dew/mcp-bookmark.git",
        "mcp-bookmark-server"
      ],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key-here"
      }
    }
  }
}

Continue (VS Code Extension)

If you use a continue workflow in your editor, add the same server configuration to the continuation setup so commands can reach the Bookmark Server directly from your MCP client.

Available tools and endpoints

The Bookmark Server exposes two primary functions to interact with bookmark data.

Security and credentials

Always protect your OpenAI API key. Do not commit keys to source control and store them securely in your host environment. The server uses the key to enable AI-powered categorization and search enhancements.

Examples and notes

Save a bookmark example: you can save a URL with a title and optional description. Later you can search for bookmarks by topic or describe the kind of resource you are looking for.