Felt (Collaborative Maps) Connector for AI agents.
11 live capabilities
Manage collaborative maps and spatial data through natural conversation.
Waiting for input…
Why people use Felt (Collaborative Maps)
Felt for GIS and Spatial Data Management
With this Connector, you just tell your agent to upload the data and style it. It handles the API calls and style objects for you, giving you a finished map in seconds.
What Vinkius changes
You get a voice-controlled interface for managing complex geographic data.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Updating field data
A researcher has new coordinates from a site visit.
- Real-world use case 02
Rapid prototyping
A planner needs a new view of a neighborhood.
- Real-world use case 03
Data cleaning
An analyst needs to remove old points from a dataset.
Complete set · 11capabilities
The complete Felt (Collaborative Maps) capability set.
These are the exact actions your AI can choose when you ask it to work with Felt (Collaborative Maps).
01—04
4 capabilities in this set.
Part of 11 available through Felt (Collaborative Maps).
- 01 Capability
Create layer
Create a new layer by uploading data types like GeoJSON, CSV, or KML. This makes it easy to bring external datasets into your map.
- 02 Capability
Delete element
Remove a specific geographic feature from an existing map layer. Use this to clean up points or lines that are no longer relevant.
- 03 Capability
Delete layer
Permanently remove a layer from your map. This helps keep your workspace organized by getting rid of old data.
- 04 Capability
Delete map
Delete an entire map from your collection. Use this when you are finished with a project and want to clear your dashboard.
05—08
4 capabilities in this set.
Part of 11 available through Felt (Collaborative Maps).
- 05 Capability
Get layer
Pull specific details and metadata for a single map layer. This provides the context needed for your agent to understand specific data points.
- 06 Capability
Get map
Retrieve the full details and metadata for a specific map. It lets your agent know the exact scope and boundaries of your current project.
- 07 Capability
List maps
Get a complete list of all maps available in your account. You can quickly see every project you have active at once.
- 08 Capability
Update element
Modify the properties of a specific geographic feature. This allows you to change the details of a point or line without recreating it.
09—11
3 capabilities in this set.
Part of 11 available through Felt (Collaborative Maps).
- 09 Capability
Update layer
Change the name or visual style of an existing layer. You can apply complex styles programmatically to change how data looks.
- 10 Capability
Create map
Generate a brand new map within your Felt account. You can set specific viewports to start your project in the right place.
- 11 Capability
Add elements
Insert new points, lines, or polygons into a map layer. This is the fastest way to populate your map with new geographic data.
Set up in minutes
One URL. Then ask Felt (Collaborative Maps) to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Felt (Collaborative Maps) from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Felt (Collaborative Maps), and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Felt (Collaborative Maps) for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Felt (Collaborative Maps) URL.
- Step 03
Save and start
Save the connection and enable Felt (Collaborative Maps) in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"felt-collaborative-maps": {
"url": "https://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Felt (Collaborative Maps)
Open Agent mode in chat and ask: "Using Felt (Collaborative Maps), help me...". 11 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"felt-collaborative-maps": {
"url": "https://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Felt (Collaborative Maps)
Ask Copilot: "Using Felt (Collaborative Maps), help me...". 11 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"felt-collaborative-maps": {
"url": "https://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Felt (Collaborative Maps)
Open Cascade and ask: "Using Felt (Collaborative Maps), help me...". 11 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"felt-collaborative-maps": {
"url": "https://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Felt (Collaborative Maps)
Ask Cline: "Using Felt (Collaborative Maps), help me...". 11 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add felt-collaborative-maps --transport http "https://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Felt (Collaborative Maps)
Ask Claude: "Using Felt (Collaborative Maps), show me...". 11 tools are ready
Where the request belongs
Work Felt can move forward.
GIS analysts and urban planners who need to move data from a spreadsheet to a visual map without manual clicking.
GIS Analyst
Updates map layers and styles as new data arrives from field teams on a Tuesday afternoon.
Urban Planner
Manages collaborative project maps and updates infrastructure elements as site plans evolve.
Logistics Coordinator
Visualizes routes and service areas by adding new elements to shared maps as delivery zones change.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsOpenStreetMap
Access and edit OpenStreetMap data. manage changesets, query map elements, and retrieve geospatial data directly from any AI agent.
Mapbox
Integrate Mapbox mapping and location services into your AI agent—access vector/raster tiles, static images, directions, and manage datasets.
ArcGIS
Access GIS services via ArcGIS. geocode addresses, search places, get routes, check elevation and discover basemap styles from any AI agent.
CARTO
Empower your AI agents to execute spatial SQL, generate routes, create driving isolines, and bulk geocode directly on CARTO.
Overpass
Access OpenStreetMap data via Overpass API. execute complex spatial queries, fetch raw map data, and monitor API status.
Nearmap (High-Res Aerial Imagery & AI)
Manage geospatial data via Nearmap. retrieve high-res aerial imagery, extract AI features, and audit survey coverage.
Bring your own AI
Change the model, client or framework. Keep Felt connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Felt.
The practical details behind the request, access and result.
Can the Felt MCP upload my data files?
Yes, you can have your agent upload data types like GeoJSON, CSV, and KML directly from public URLs into your map layers.
How do I change the style of a layer using this?
You can simply describe the style you want to your AI client, and it will use the update_layer capability to apply those visual changes.
Can I use this to manage multiple maps at once?
Yes, you can list all your maps, create new ones, or delete old projects using natural language commands.
Does this work for urban planning projects?
It is perfect for urban planning. You can manage project maps, update infrastructure elements, and share them with your team.
How does the AI know which map to edit?
The agent can list your maps to see what's available or you can specify the map name in your request.
Can I delete old data from my maps?
You can ask your agent to remove specific points, lines, or entire layers to keep your maps clean and up to date.
Can I upload my own geographic data files to a map?
Yes! Use the create_layer capability by providing a public URL to your GeoJSON, CSV, or KML file. The server will initiate the upload and processing into your specified Felt map.
How do I add a specific point or shape to an existing layer?
You can use the add_elements capability. Simply provide the layer_id and a JSON array of GeoJSON features (points, lines, or polygons) you want to add to that layer.
Is it possible to change the visual style of a map layer?
Yes. Use the update_layer capability and provide a 'Felt Style Object' (FSO) in the style parameter to programmatically change colors, icons, or visibility rules.
One connection away
Give your agent a direct line to Felt.
Connect Felt once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available