How to Use the Felt (Collaborative Maps) MCP in Vercel AI SDK

Q: How do I stream map creation using Felt (Collaborative Maps) and Vercel AI SDK?

You need to initialize the client using createMCPClient and pass the tools directly to streamText. When the agent calls createmap, the UI can capture the tool execution state to show the map container immediately.

Q: Can I handle large spatial file uploads with Felt (Collaborative Maps) in Vercel AI SDK?

Yes, you can. The agent uses createlayer which natively supports GeoJSON, CSV, KML, and Shapefiles. Because it runs on Edge-compatible routes, you avoid serverless timeout issues during large uploads.

Q: What happens to active map connections when a serverless function spins down?

You must always call mcpClient.close() to clean up active connections. This ensures your serverless environment doesn't leak resources or leave dangling SSE connections.

Render live collaborative maps directly in your React UI by connecting the Felt MCP Server to your Vercel AI SDK application.

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 Vercel AI SDK

Create your Vinkius account to connect Felt (Collaborative Maps) to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Live Maps with Vercel AI SDK

This MCP Server lets your agent run `create_map` to instantly render interactive canvases when a user requests a map. You don't make the user stare at a loading spinner while some background job processes. Behind the scenes, the agent calls `create_layer` to import the raw GIS files. It streams the progress directly to the browser, so the UI updates element by element as the data lands.

Push GeoJSON and KML Directly to the Browser

This MCP Server exposes `create_layer` to let your agent parse and upload geographic boundaries instantly when a user drops a shapefile or KML into your chat. Stop writing custom backend parsers for spatial files. Once the raw layer is set up, the agent can call `add_elements` to inject custom markers or lines based on user chat prompts. The map on the screen updates live without a full page refresh.

Direct Map Editing via Conversational UI

This MCP Server uses `update_element` to let your agent modify map features on the fly based on natural language instructions. Your users can modify map features by just talking to your interface. If someone makes a mistake, the agent runs `delete_element` or `delete_layer` to clean up the workspace. This turns your static map component into a fully collaborative whiteboard driven by natural language.

Setup guide

Set up Felt (Collaborative Maps) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Felt (Collaborative Maps) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Felt (Collaborative Maps) transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You need to initialize the client using `createMCPClient` and pass the tools directly to `streamText`. When the agent calls `create_map`, the UI can capture the tool execution state to show the map container immediately.

Yes, you can. The agent uses `create_layer` which natively supports GeoJSON, CSV, KML, and Shapefiles. Because it runs on Edge-compatible routes, you avoid serverless timeout issues during large uploads.

You should never expose your API keys to the browser. Keep your token secure on your server or within the Vinkius managed environment, routing all tool calls through the secure back-end MCP connection.

You must always call `mcpClient.close()` to clean up active connections. This ensures your serverless environment doesn't leak resources or leave dangling SSE connections.

Your raw coordinate data and GeoJSON geometries are sent directly to the map canvas through an ephemeral V8 sandbox. Vinkius does not store your spatial datasets, ensuring your proprietary geographic boundaries remain strictly private.

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