 Courses from Domitrius Clark

JavaScript® (often shortened to JS) is a lightweight, interpreted, object-oriented language with first-class functions, most known as the scripting language for Web pages, but used in many non-browser environments as well such as node.js or Apache CouchDB. It is a prototype-based, multi-paradigm scripting language that is dynamic, and supports object-oriented, imperative, and functional programming styles.

javascript

Here we will use the `some` Method from a JavaScript  Array to handle throwing an error when we try to create a user object with an email that already exists in an array of users. 

Error handling with the JavaScript Array#some method

Cursor's AI Agent has the abilitly to invoke MCP tools, but they lack direct access to your project. This lesson shows how to build custom MCP (Model Context Protocol) server tools that bridge this gap. Learn to define tool parameters using Zod schemas and the crucial `.describe()` method to explicitly request necessary context from the Cursor environment *before* your tool runs. See how the AI gathers this information (like Git status or version via terminal commands, or web search results) and passes it to your tool, enabling powerful, context-aware automation.

**Workflow demonstrated in this lesson:**

*   Scaffold a basic MCP server using a Cloudflare template (`pnpm create cloudflare`).
*   Run the MCP server locally and configure it in Cursor settings.
*   Define MCP tools (e.g., `status`) within the server code (`index.ts`).
*   Specify required context for tools using Zod schema parameters and `.describe()` (e.g., requesting "The status of the git repository").
*   Interact with the Cursor Agent using natural language (e.g., "Please check the status").
*   Observe the Agent's thought process: identifying the need for specific context based on the `.describe()` text.
*   See the Agent automatically using its *own* tools (like `run_terminal_cmd` or `web_search`) to gather the requested context *before* calling your MCP tool.
*   Watch the Agent call your MCP tool, passing the gathered local context (Git status, version, etc.) as arguments.
*   Receive the final response from the Agent, incorporating the information provided by your local MCP tool.

**Key benefits:**

*   Allows Cursor's AI to access and reason about information from your local machine (Git status, versions, file contents, etc.).
*   Enables the creation of AI tools that directly interact with or report on your local development environment.
*   Demonstrates the power of using `.describe()` in Zod schemas to guide the AI in gathering necessary context automatically.
*   Unlocks advanced automation possibilities by combining AI reasoning with local machine access.

John Lindquist

Create a Custom MCP that Calls Cursor Tools

Vimium's Vomnibar is a "command palette"-like search tool for your open tabs, browser history, and bookmarks. We can search through and jump to any tab open across browser windows. We can also do a generalized search with results that also include browser history and bookmarks which can either be opened in the current tab or a new tab. If you're anything like me, you open tons of tabs and visit hundreds of webpages over the course of a week. The vomnibar puts all of that at your fingertips.

Josh Branchaud

Open Tabs, Browser History, and Bookmarks with the Vomnibar

Vimium's Vomnibar is a "command palette"-like search tool for your open tabs, browser history, and bookmarks.

Another aspect of Vimium's configurability is customizable key mappings. We can add new mappings and override existing ones. If there is a certain Vimium feature you want to make easier to trigger, adjust the key mapping to suit your needs.

Configure Custom Vimium Key Mappings

Another aspect of Vimium's configurability is customizable key mappings. We can add new mappings and override existing ones.

Many aspects of Vimium can be configured in order to bend the tool to your specific needs and use cases. We look at how to configure what sites turn off Vimium, the default search engine, link hint characters, and other basic settings. We also see how both insert mode and searching a visual selection work. Custom keymappings and custom search engines are covered in subsequent lessons.

Configure Basic Aspects of Vimium

Many aspects of Vimium can be configured in order to bend the tool to your specific needs and use cases.

Vimium's "marks" feature lets you mark positions in the current tab and across tabs. These are positional markers that you can jump back to. For instance, as you browse a huge page of documentation or a massive forum discussion, you can leave a series of "dog ears" to sections or conversations that you'll later want to revisit. Each tab supports its own set of lower-case letter marks. Upper-case letter marks are shared across tabs allowing you to seamlessly move between a specific set of tabs regardless of how they are arranged.

Set Marks on a Vimium Webpage You Want to Jump Back To

Vimium's "marks" feature lets you mark positions in the current tab and across tabs. These are positional markers that you can jump back to.

Vimium's `yy` shortcut makes quick work of grabbing the URL for the current page. I find this useful for linking to an article in my notes or sharing a web page with my team in Slack/Discord. We'll get a glimpse at a couple other features like `gi` (for "go to input") and `o` to open the URL on the clipboard.

Grab and Open URLs with Vimium

Vimium's `yy` shortcut makes quick work of grabbing the URL for the current page.

An introduction to "Why Use Vimium" and how to install it in your browser of choice. Though this entire course uses Chrome, Vimium is also available for Edge and Firefox. There is a lot that Vimium can do — on-page navigation, moving between tabs, interacting with links and other page elements, and much more. We'll get into all of that in the following lessons.

Install and Start Using Vimium

An introduction to "Why Use Vimium" and how to install it in your browser of choice

A powerful navigation and interaction feature, and probably my most used Vimium feature, is Link Hints. By hitting `f`, we prompt Vimium to overlay link hints for every visible link, button, and interactive HTML element (e.g. a text area). By typing the keys corresponding to a link hint, we effectively click that link or element. We also look at a few page movement commands like scrolling up (`k`) and down (`j`) as well as jumping to the top of a page (`gg`) and to the bottom (`G`). Putting all of these together, we can get into a fluid and efficient flow for common browser tasks.

Follow Links and Fill Forms with Vimium

A powerful navigation and interaction feature, and probably my most used Vimium feature, is Link Hints.

The Vimium Chrome extension enhances page navigation and searching. By pressing forward slash, users enter find mode to search terms on the page. Additional keys like 'N' and Shift+N help navigate through search results forwards and backwards, respectively. The extension proves especially useful on complex web pages, like Stack Overflow, for quickly locating specific sections like answers or share links without reading through all the content.


Navigate using find with Vimium

With these advanced URL manipulation commands we have a whole new way to think about traversing between locations on a website. This is especially useful for sites like GitHub that use a hierarchical URL structure. Since each layer of the URL is a valid page, we can move up that structure (with `gu`) and edit the current URL (with `ge`) to navigate somewhere else.

Traverse a Site with Advanced URL Manipulation with Vimium

With these advanced URL manipulation commands we have a whole new way to think about traversing between locations on a website.

Domitrius Clark

Search Results

Error handling with the JavaScript Array#some method