How to Use the Felt (Collaborative Maps) MCP in Windsurf

Q: How do I connect the Felt (Collaborative Maps) MCP Server to Windsurf?

Add the server block to your /.codeium/windsurf/mcpconfig.json file. Once saved, Cascade auto-discovers the tools and registers the MCP server.

Q: Can Cascade in Windsurf handle large GeoJSON uploads via Felt (Collaborative Maps)?

Yes, Cascade handles large files by invoking createlayer with your local dataset path. It parses the file and uploads it directly to Felt's servers.

Q: How do I update map markers in real time using Felt (Collaborative Maps) on Windsurf?

You tell Cascade to monitor your data source, and it uses updateelement to refresh markers automatically. Cascade uses the MCP server to run updates without requiring manual confirmation for every single pin.

Q: Can I list my existing maps within the IDE?

Yes, the listmaps tool lets you view all your maps inside the Cascade panel. You can select one to edit without leaving your workspace.

Build live collaborative maps inside Windsurf by letting Cascade chain your geospatial data tasks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Felt (Collaborative Maps) MCP to Windsurf

Create your Vinkius account to connect Felt (Collaborative Maps) 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 Felt (Collaborative Maps) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Maps Autonomously with Windsurf

The `create_map` tool allows Windsurf to spin up fresh collaborative canvases without you writing boilerplate code. Cascade takes your prompt, creates the map, and grabs the ID to use in the next step of its chain. Once the map is live, Cascade doesn't stop. It immediately coordinates with other tools to structure your spatial layers, meaning you get a ready-to-share visualization from a single prompt.

Dynamic Layer Styling

The `create_layer` tool lets your agent upload raw GeoJSON, KML, or CSV data directly to your active map. Cascade reads your local files, identifies the coordinate columns, and pushes the data to Felt in one shot. If the visualization needs a tweak, Cascade uses `update_layer` to adjust styles or bounds. You don't have to manually format JSON payloads because the agent translates your instructions into the exact schema Felt expects.

Real-Time Feature Manipulation

The `add_elements` tool lets Windsurf insert specific pins, lines, or polygons onto your layer based on live application data. Cascade monitors your local code state and pushes updates to the map as things change. When items need to be removed or modified, the agent calls `delete_element` or `update_element` on the fly. This keeps your team's shared map perfectly synchronized with your actual database records without manual intervention.

Setup guide

Set up Felt (Collaborative Maps) 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 Felt (Collaborative Maps) 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 Felt (Collaborative Maps) payment history." If connected, Cascade will call the Felt (Collaborative Maps) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "felt-collaborative-maps-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 Felt. 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 Felt (Collaborative Maps) 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 Felt (Collaborative Maps) MCP in Windsurf

Add the server block to your `~/.codeium/windsurf/mcp_config.json` file. Once saved, Cascade auto-discovers the tools and registers the MCP server.

Yes, Cascade handles large files by invoking `create_layer` with your local dataset path. It parses the file and uploads it directly to Felt's servers.

You tell Cascade to monitor your data source, and it uses `update_element` to refresh markers automatically. Cascade uses the MCP server to run updates without requiring manual confirmation for every single pin.

Yes, the `list_maps` tool lets you view all your maps inside the Cascade panel. You can select one to edit without leaving your workspace.

Your spatial data and coordinates travel securely through Vinkius's zero-trust sandboxed MCP environment directly to Felt. No geographic information is stored or cached on intermediate servers during the process.

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