
Connect Felt Collaborative Maps to ChatGPT and Claude
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Build and edit collaborative maps through natural conversation.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 11 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 11 available through Felt.
- 01
Create layer
This capability uploads geographic data to a Felt map. It supports formats like GeoJSON, CSV, KML, and Shapefiles.
- 02
Delete element
Use this to remove a specific geographic element from a map.
- 03
Delete map
This capability deletes an entire Felt map.
- 04
Get map
This capability retrieves detailed metadata and information for a specific Felt map.
05-08
4 capabilities in this set.
Part of 11 available through Felt.
- 05
List maps
This capability returns a list of all your accessible Felt maps.
- 06
Update layer
Use this to modify the properties or settings of an existing Felt layer.
- 07
Add elements
This capability adds new geographic features to a specified Felt layer.
- 08
Create map
This capability generates a brand new Felt map.
09-11
3 capabilities in this set.
Part of 11 available through Felt.
- 09
Delete layer
Use this to remove a specific layer from a map.
- 10
Get layer
This capability fetches the details and metadata for a specific Felt layer.
- 11
Update element
This capability allows you to modify existing geographic elements within a layer.
Real work
What teams actually run
Rapid Prototyping
A data scientist tells their agent to create a map and upload a GeoJSON file to visualize a new dataset immediately.
Field Data Updates
An urban planner asks their agent to add new points to a map as soon as field observations are recorded.
Route Visualization
A logistics manager has their agent add service area polygons to a shared map for team review.
Map Cleanup
A researcher asks their agent to delete outdated layers or specific elements from a project map.
Automate a task
Put Felt to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Felt works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Felt to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
1022ms average. Fast in production.
Felt is checked daily against the live service.
- Fastest day
- 701ms
- Slowest day
- 1281ms
- 14-day trend
- Slowing+13%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 11 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Felt, so you can see the experience inside your AI.
It does not authenticate your account with Felt. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Felt Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Felt capabilities are ready to use.
{
"mcpServers": {
"felt-collaborative-maps-mcp": {
"url": "https://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Felt in Claude and other AIs
Who it's for
Built for the work Felt owners hand off.
This MCP is built for professionals working with spatial data who want to automate map creation and editing.
- 01
GIS Analysts
They use the agent to prototype maps and upload datasets quickly.
- 02
Urban Planners
They manage collaborative project maps and update them with field data.
- 03
Logistics Teams
They visualize routes and service areas by adding elements to shared maps.
FAQ
Questions Felt owners ask.
- 01
What file formats can I upload to Felt using this MCP?
The agent can upload GeoJSON, CSV, KML, and Shapefiles by using a public URL for the data.
- 02
Which AI clients can I use with this MCP?
You can use this MCP with any compatible client, including Claude, Cursor, Windsurf, and VS Code.
- 03
Can I change how my map layers look?
Yes, the agent can update layer names and apply visual styles using the Felt Style Object.
- 04
Do I need to host the MCP myself?
No, Vinkius hosts and manages the MCP for you. You just connect your client and start working.
- 05
Can I edit specific shapes on a map?
Yes, you can use the agent to add, update, or delete specific points, lines, and polygons.
- 06
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.
- 07
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.
- 08
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.
Explore
More in Collaboration
Data.gov Catalog AI Connector
Access the official US Government open data catalog. Search thousands of datasets, organizations, and spatial
ViewMapbox (Maps & Geospatial) AI Connector
Build with location data via Mapbox — geocode addresses, calculate routes, and solve trip optimization.
ViewHevo Data (ETL & Data Pipeline) AI Connector
Manage data pipelines via Hevo — list pipelines, monitor destinations, and track usage.
ViewMode (Collaborative Data Platform) AI Connector
Manage collaborative analytics via Mode — list data reports, explore organizational spaces, and audit data sou
View
Suggestions
Data Pipeline Prover AI Connector
A data team asked an AI to build an ETL pipeline. No schema contract. No idempotency. No freshness SLA. The pi
Viewdata.world AI Connector
Equip your AI agent to discover and manage data assets, projects, and queries directly via the data.world API.
ViewCARTO AI Connector
Empower your AI agents to execute spatial SQL, generate routes, create driving isolines, and bulk geocode dire
ViewMap-Reduce Partition Planner AI Connector
Deterministic calculator for partitioning and scheduling map-reduce workloads.
View
Connect Felt to Claude, Cursor, ChatGPT & more
