How to Use the Felt (Collaborative Maps) MCP in OpenAI Agents SDK

Q: How do I connect Felt (Collaborative Maps) to my OpenAI Agents SDK project?

Install the MCP client and define your server using MCPServerStreamableHttp. Pass that server instance directly into your agent constructor to enable automatic tool discovery.

Q: Can I use Felt (Collaborative Maps) to update elements during an OpenAI Agents SDK session?

Yes. You just call the updateelement tool within your agent's execution logic. It pushes the change to your map instantly.

Q: Does Felt (Collaborative Maps) work with OpenAI Agents SDK for bulk data?

It does. You can batch your data using createlayer to handle larger files efficiently. This keeps your agent's performance stable during high-volume operations.

Use the Felt (Collaborative Maps) MCP Server to push geographic data directly from your OpenAI Agents SDK production flows.

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 OpenAI Agents SDK

Create your Vinkius account to connect Felt (Collaborative Maps) to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate map creation with OpenAI Agents SDK

Your agent can spin up new workspaces instantly using `create_map`. It handles the heavy lifting so your production environment stays focused on logic rather than manual map setup. Once the map is ready, you can push structured geographic data via `add_elements`. This turns raw coordinate streams into visual context without leaving your agent's execution loop.

Sync spatial data from your OpenAI agents

Keep your map layers current by piping data through `create_layer`. Whether you are handling GeoJSON or CSV, the MCP Server manages the ingestion process while your agent maintains state. When data changes, call `update_element` to keep the map accurate. You get real-time updates without the overhead of manual interface interactions.

Manage map infrastructure via code

Clean up your workspace by using `delete_layer` or `delete_map` when a project concludes. This ensures your map environment doesn't become cluttered with obsolete test data. Use `get_map` or `get_layer` to pull current metadata back into your agent. This visibility allows your system to make smarter decisions based on the actual state of your collaborative maps.

Setup guide

Set up Felt (Collaborative Maps) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Felt (Collaborative Maps) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Felt (Collaborative Maps) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Felt (Collaborative Maps) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Felt (Collaborative Maps) Agent",
            instructions="You have access to Felt (Collaborative Maps) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the MCP client and define your server using `MCPServerStreamableHttp`. Pass that server instance directly into your agent constructor to enable automatic tool discovery.

Yes. You just call the `update_element` tool within your agent's execution logic. It pushes the change to your map instantly.

It does. You can batch your data using `create_layer` to handle larger files efficiently. This keeps your agent's performance stable during high-volume operations.

Your data sits on Felt's servers. The MCP server acts only as a bridge for your agent to send commands and retrieve map state.

Vinkius handles the auth layer with your endpoint token. Your agent only interacts with the specific map resources you authorize.

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