Compatible with every major AI agent and IDE
What is the Felt (Collaborative Maps) MCP Server?
Connect Felt to your AI agent to take full control of your collaborative mapping workflows through natural conversation. This server allows you to manage maps, layers, and geographic elements without leaving your workspace.
What you can do
- Map Management — List all accessible maps, create new ones with specific viewports, and retrieve detailed metadata or delete maps.
- Data Uploads & Layers — Create layers by uploading geographic data (GeoJSON, CSV, KML) via public URLs and monitor their processing status.
- Dynamic Styling — Update layer names and apply complex visual styles using the Felt Style Object (FSO) programmatically.
- Element Manipulation — Add, update, or delete specific geographic features like points, lines, and polygons within your map layers.
- Spatial Analysis Context — Fetch map and layer details to provide your AI with the necessary context for spatial reasoning.
How it works
- Subscribe to this server
- Enter your Felt API Token
- Start building and editing maps from Claude, Cursor, or any MCP-compatible client
Who is this for?
- GIS Analysts & Data Scientists — quickly prototype maps and upload datasets for visualization using simple commands.
- Urban Planners & Researchers — manage collaborative project maps and update elements as field data comes in.
- Logistics & Ops Teams — visualize routes and service areas by programmatically adding elements to shared maps.
Built-in capabilities (11)
Add elements to a Felt layer
Supports GeoJSON, CSV, KML, Shapefiles, etc. Create a layer (Upload Data) to a Felt map
Create a new Felt map
Delete a Felt element
Delete a Felt layer
Delete a Felt map
Get details for a specific Felt layer
Get details for a specific Felt map
List Felt maps
Update a Felt element
Update a Felt layer
Why Cursor?
Cursor's Agent mode turns Felt (Collaborative Maps) into an in-editor superpower. Ask Cursor to generate code using live data from Felt (Collaborative Maps) and it fetches, processes, and writes. all in a single agentic loop. 11 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
Felt (Collaborative Maps) in Cursor
Felt (Collaborative Maps) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Felt (Collaborative Maps) to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Felt (Collaborative Maps) in Cursor
The Felt (Collaborative Maps) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 11 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Felt (Collaborative Maps) for Cursor
Every tool call from Cursor to the Felt (Collaborative Maps) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Bear
10 toolsManage your Bear notes via AI — search, create, and organize your markdown knowledge base autonomously.

Trengo
12 toolsManage customer conversations across WhatsApp, email, chat, and social from one shared inbox your whole team can use.

ShipHero
8 toolsManage e-commerce logistics via ShipHero — track orders, monitor inventory levels, and handle warehouse movements directly from your AI agent.

Amplemarket
8 toolsSales automation and lead generation — manage sequences, leads, and custom signals via AI.
