Cursor launches Customize page to centralize plugins, skills, and MCPs
TL;DR
Cursor adds a Customize page that centralizes plugins, skills, MCPs, subagents, rules, and hooks with a marketplace leaderboard, prebuilt canvases, and repository imports from GitLab, BitBucket, and Azure DevOps.
What changed
Cursor now offers a single Customize page that brings together plugins, skills, MCPs, subagents, rules, and hooks for Developers and Vibe Builders. The page includes a marketplace leaderboard along with prebuilt plugin canvases for data visualization and Atlassian integration. It also adds support for importing repositories from GitLab, BitBucket, or Azure DevOps.
Why it matters
This setup helps Basic Users manage customizations without scattered settings while giving Vibe Builders quick access to marketplace options. For teams relying on Atlassian tools the integration provides a ready canvas that speeds up workflow setup. Developers benefit from centralized control that reduces time spent on configuration tasks.
What to watch for
Compare the new page against manual setups in VS Code to see differences in plugin handling. Basic Users should verify by importing a sample repository from GitLab and checking the leaderboard rankings.
Who this matters for
- Vibe Builders: Use the marketplace leaderboard to find and install top-rated subagents and rules for your apps.
- Basic Users: Import your GitLab or BitBucket repos directly to start using AI features on your existing code.
Harsh’s take
Cursor is moving fast to become the definitive AI operating system for code. By centralizing Model Context Protocol (MCP) servers and subagents into a single marketplace, they are solving the fragmentation that plagues the VS Code ecosystem. This is a direct play for the 'Vibe Builder' market: people who want to orchestrate complex software without manually configuring JSON files or environment variables.
The addition of Atlassian and data visualization canvases suggests Cursor is moving beyond simple text completion toward full-stack workflow automation. For operators, the takeaway is clear: stop treating your IDE as a text editor and start treating it as a platform. If you are not using MCPs to connect your codebase to external data sources like Jira or SQL databases, you are leaving massive productivity gains on the table.
by Harsh Desai
About Cursor
View the full Cursor page →All Cursor updatesGo deeper
More from Cursor
- FeatureCursor adds cloud agent management to Agents Window
Cursor sets up cloud environments in under 10 minutes and saves configurations as reusable snapshots. The update adds cloud subagents via /in-cloud for long-running tasks with seamless local-to-cloud handoffs.
- FeatureCursor introduces /automate skill for configuring automation triggers
Cursor Automations introduces the /automate skill to configure triggers, instructions, and tools in plain language. It adds Slack emoji triggers, five new GitHub triggers, and a computer use tool enabling cloud agents to produce demos or artifacts.
- FeatureCursor supports running and managing cloud agents in Agents Window
Cursor adds support for running and managing cloud agents in the Agents Window. It enables cloud environment setup in under 10 minutes and isolated subagents via /in-cloud.