How to Use the Felt (Collaborative Maps) MCP in Claude Code

Q: How do I add the Felt (Collaborative Maps) MCP Server to Claude Code?

Run the claude mcp add command with the HTTP transport flag and the server URL. This saves the configuration directly to your /.claude.json file.

Q: Does this CLI integration support deleting layers?

Yes, the CLI can run deletelayer to remove outdated data layers instantly. You just specify the layer ID in your terminal prompt.

Run headless GIS workflows and manage Felt maps directly from your terminal using Claude Code.

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 Claude Code

Create your Vinkius account to connect Felt (Collaborative Maps) to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scriptable Map Control with Claude Code

The `create_map` tool allows Claude Code to spin up collaborative maps directly from your command line interface. You can pipe terminal outputs or script variables straight into a new map instance. This headless control makes it easy to integrate mapping into your CI/CD pipelines. You can generate a fresh map for every build or deployment run without opening a browser.

Terminal-Based Layer Management

The `create_layer` tool lets you push local spatial datasets like KML or CSV files to Felt from your shell. Claude Code handles the file reading and uploads the payload through the MCP transport. If a deployment script needs to refresh data, Claude Code runs `delete_layer` followed by a new upload. This ensures your production maps always display the latest spatial datasets.

Automated Element Synchronization

The `add_elements` tool enables Claude Code to inject live server metrics or geographic coordinates into your map layers. You can set up cron jobs that use the CLI to update map markers. To keep the map clean, Claude Code uses `update_element` to modify existing markers as your backend state changes. This gives your team a real-time operational dashboard built on Felt.

Setup guide

Set up Felt (Collaborative Maps) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see felt-collaborative-maps-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Felt (Collaborative Maps) transactions." It will automatically discover and invoke the available Felt (Collaborative Maps) tools.

Terminal

claude mcp add --transport http felt-collaborative-maps-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "felt-collaborative-maps-mcp": {
      "type": "url",
      "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 Claude Code

Run the `claude mcp add` command with the HTTP transport flag and the server URL. This saves the configuration directly to your `~/.claude.json` file.

Yes, you can script Claude Code to loop through datasets and call `create_map` for each region. It runs headlessly in your terminal or automation server.

Run a prompt asking Claude Code to show your maps, and it will execute the MCP tool `list_maps`. The results print directly to your terminal output.

Yes, the CLI can run `delete_layer` to remove outdated data layers instantly. You just specify the layer ID in your terminal prompt.

Your API tokens are stored locally in your encrypted Claude Code configuration, and spatial coordinates are sent over TLS directly to Felt. No data is stored on Vinkius's ephemeral MCP execution nodes.

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