# Felt MCP for AI Agents AI Agent Connect

> Felt (Collaborative Maps) lets you build and manage maps through your AI client. You can upload geographic data like GeoJSON or CSV, create new maps with specific views, and update styles or individual points on a map using natural language. It turns your AI into a GIS operator.

## Overview
- **Category:** collaboration
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_uEA3uCm62J6X4qOlPXCYtzQ5GgmnFZvYo8P4r3S8/ai-agent-connect
- **Tags:** gis, mapping, spatial-data, collaborative-editing, geospatial, data-visualization

## Description

You can handle your entire geospatial workflow without switching between tabs or manual editing tools. Instead of hunting for specific buttons to style a layer or manually uploading files, you just tell your AI client what needs to happen. This Connector lets you create new maps, upload data from public URLs, and adjust visual styles on the fly. If you need to change a specific point or a line on a map, you can just ask for it. It handles the heavy lifting of updating geographic elements while you focus on the analysis. By connecting this to the Vinkius catalog, you get a direct line to Felt's collaborative mapping features. You'll spend less time fiddling with map settings and more time actually interpreting the data. It makes managing complex layers as simple as having a conversation. You can move from a raw data file to a styled, shared map in a few seconds without ever having to leave your chat window. This is a game changer for people who need to see spatial patterns quickly. Whether you are visualizing new transit routes, updating site plans, or mapping out logistics hubs, you can now manage those layers through simple commands. It takes the friction out of data visualization by making the map respond to your instructions in real time.

## Tools

### 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.

### 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.

### delete_layer
Permanently remove a layer from your map. This helps keep your workspace organized by getting rid of old data.

### delete_map
Delete an entire map from your collection. Use this when you are finished with a project and want to clear your dashboard.

### 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.

### 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.

### list_maps
Get a complete list of all maps available in your account. You can quickly see every project you have active at once.

### 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.

### update_layer
Change the name or visual style of an existing layer. You can apply complex styles programmatically to change how data looks.

### create_map
Generate a brand new map within your Felt account. You can set specific viewports to start your project in the right place.

### 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.

## Prompt Examples

**Prompt:** 
```
What maps do I have in Felt?
```

**Response:** 
```
I've pulled your map list. You have 3 active maps:

- **Urban Planning 2024**
- **Logistics Hubs**
- **Environmental Study**

Which one should we work on?
```

**Prompt:** 
```
Can you make a new map for my city project?
```

**Response:** 
```
I've created the map for your 'City Project'. It's ready for you to view and start adding layers.
```

**Prompt:** 
```
Put a new point on the main street in my current map.
```

**Response:** 
```
I've added that point to the layer. You can see it on the main street now. Did you want me to add any other points nearby?
```

## Capabilities

### Create new maps with specific views
Generate a new map and set the initial camera position with a single command.

### Upload geographic data from public URLs
Bring in GeoJSON, CSV, and KML files directly from the web into your layers.

### Update layer names and visual styles
Change how your data looks and what it's called without manual styling.

### Add or delete specific map elements
Insert or remove points, lines, and polygons on your map in real time.

### Fetch map metadata for spatial reasoning
Give your agent the necessary context to understand your map's data and scope.

## Use Cases

### Updating field data
A researcher has new coordinates from a site visit. They ask the agent to use add_elements to put them on the shared project map immediately.

### Rapid prototyping
A planner needs a new view of a neighborhood. They ask the agent to use create_map with a specific viewport to start a new project.

### Data cleaning
An analyst needs to remove old points from a dataset. They ask the agent to use delete_element to clean up the layer for a presentation.

### Style adjustments
A logistics lead wants to change a route color to indicate high traffic. They ask the agent to use update_layer to apply a new visual style.

## Benefits

- Skip the manual upload process by using create_layer to pull data from public URLs directly into your project.
- Update map visuals instantly using update_layer to change styles and names without opening a browser or clicking through menus.
- Keep your workspace organized by using list_maps to quickly find and switch between different projects in your account.
- Modify specific map points on the fly with add_elements and update_element to reflect real-time changes in the field.
- Get instant spatial context by using get_map to feed map metadata into your AI client for better reasoning on your data.
- Remove outdated information quickly by using delete_element or delete_layer to keep your collaborative maps clean.

## How It Works

The bottom line is you get a voice-controlled interface for managing complex geographic data.

1. Subscribe to the Felt MCP on Vinkius
2. Provide your Felt API Token in the configuration
3. Start creating or editing maps via your AI client

## Frequently Asked Questions

**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 tool 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` tool 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` tool. 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` tool and provide a 'Felt Style Object' (FSO) in the `style` parameter to programmatically change colors, icons, or visibility rules.