How to Use the Amazing Marvin MCP in Windsurf

Q: How does Windsurf Cascade interact with my Amazing Marvin tasks?

Cascade reads your schedule using gettodayitems and updates it as you write code. It operates in the background to sync your real-world progress with your task list.

Q: Can I create a new project in Amazing Marvin using Windsurf?

Yes, you can ask Cascade to set up your workspace. It uses addproject and addcategory to build out your Marvin hierarchy based on your active code repository.

Q: Does Windsurf support time tracking with this MCP Server?

This integration lets Windsurf call starttracking and stoptracking directly from your workspace. Your actual coding hours map perfectly to your Marvin tasks.

Q: Can Cascade check sub-tasks and nested structures?

Yes, Cascade uses getchildren to inspect your existing Marvin structure. It figures out what needs to be done next and schedules the work accordingly.

Let Windsurf Cascade manage your Amazing Marvin schedule, build tasks, and track your time while you write code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazing Marvin MCP to Windsurf

Create your Vinkius account to connect Amazing Marvin to Windsurf 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 Amazing Marvin with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cascade schedules your day with this MCP Server

When you start your morning, Cascade doesn't just look at your local code files. It queries your active list using `get_today_items` to see what you actually planned to finish. You get a clear picture of your day without opening a browser. If a bug fix takes longer than expected, Cascade uses `update_task` to reschedule your next priority. It shifts your Marvin agenda dynamically based on your actual coding speed.

Automatic time tracking directly inside Windsurf

Stop leaving your IDE to punch a clock. When Cascade starts working on a feature branch, it fires `start_tracking` on your active Marvin task to log your development hours. The moment you run your tests and confirm the build works, the agent invokes `stop_tracking` and calls `mark_done`. Your timesheets stay accurate because your editor manages them in the background.

Structure your roadmap from the editor

Building a new microservice usually means manual planning. Cascade breaks down the architecture and runs `add_project` and `add_category` to mirror your code structure inside your Marvin workspace. Your backlog is instantly populated with specific, actionable dev tasks via this MCP server without manual data entry. It then populates those categories with individual technical steps using `add_task`.

Setup guide

Set up Amazing Marvin MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Amazing Marvin MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Amazing Marvin payment history." If connected, Cascade will call the Amazing Marvin tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "amazing-marvin-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 Amazing Marvin. 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 Amazing Marvin 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 Amazing Marvin MCP in Windsurf

Cascade reads your schedule using `get_today_items` and updates it as you write code. It operates in the background to sync your real-world progress with your task list.

Yes, you can ask Cascade to set up your workspace. It uses `add_project` and `add_category` to build out your Marvin hierarchy based on your active code repository.

This integration lets Windsurf call `start_tracking` and `stop_tracking` directly from your workspace. Your actual coding hours map perfectly to your Marvin tasks.

Yes, Cascade uses `get_children` to inspect your existing Marvin structure. It figures out what needs to be done next and schedules the work accordingly.

Vinkius hosts this MCP integration in a secure, ephemeral V8 isolate sandbox. Your Marvin API keys, task details, and time logs are never cached or exposed to third parties.

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