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

Q: How do I register Felt (Collaborative Maps) tools inside a Mastra AI agent?

Initialize the MCPClient with your Vinkius endpoint URL. Then, call mcpClient.listTools() and spread those tools directly into your agent's tool configuration array.

Q: Can I use Felt (Collaborative Maps) inside a Mastra AI workflow with conditional branches?

Absolutely. You can write a step that calls getlayer to fetch geometric data, then use Mastra's branching logic to decide whether to run updatelayer or trigger an alert.

Build resilient, multi-step mapping workflows using Mastra AI and the Felt MCP Server.

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 Mastra AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Map Creation with the Mastra AI Workflow Engine

This MCP Server provides `create_map` and `create_layer` to let your agent build map layers with automatic retry logic. Building map layers can fail when external APIs rate limit your requests. If a bulk upload fails halfway through, Mastra handles the exponential backoff automatically. Your agent won't leave maps in a half-finished state because the workflow engine recovers the session and resumes uploading.

Branch Workflows Based on Map Elements

This MCP Server exposes `get_map` and `list_maps` to let your agent inspect existing layouts before deciding to modify spatial data. You can design workflows that check map state before taking action. When specific conditions are met—like a layer exceeding a certain size—the workflow branches. It can trigger `delete_layer` to clean up old draft data or spin up a fresh map using `create_map`.

Human-in-the-Loop Element Approvals

This MCP Server uses `update_element` to let your agent draft map modifications that require human review before going live. You don't always want your agent altering public maps autonomously. The agent drafts the changes using `get_layer`, presents the proposed spatial edits to an operator, and only executes `add_elements` once a human clicks approve. This keeps your production maps clean and accurate.

Setup guide

Set up Felt (Collaborative Maps) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Felt (Collaborative Maps) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "felt-collaborative-maps-mcp-client",
  servers: {
    "felt-collaborative-maps-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Felt (Collaborative Maps) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Felt (Collaborative Maps) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Felt (Collaborative Maps) transactions"
);
console.log(result.text);

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 Mastra AI

Initialize the `MCPClient` with your Vinkius endpoint URL. Then, call `mcpClient.listTools()` and spread those tools directly into your agent's tool configuration array.

Absolutely. You can write a step that calls `get_layer` to fetch geometric data, then use Mastra's branching logic to decide whether to run `update_layer` or trigger an alert.

Mastra features a built-in workflow engine that handles retries and backoff. If you push too many elements at once via `add_elements`, the system pauses and retries without failing the entire run.

Yes, it does. The TypeScript client auto-detects the transport type exposed by your managed Vinkius endpoint, making configuration a single-line URL setup.

Your geographic files and layer attributes pass through memory in an ephemeral, zero-trust sandbox. No spatial data is cached or stored permanently on the middleware servers.

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