How to Use the Fusioo MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK read my Fusioo custom apps?

Yes. The agent uses listapps to find the target app and getappschema to understand its structure. It then knows exactly how to format requests for that specific database.

Build production-ready agents that manage your Fusioo workspaces with the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fusioo MCP to OpenAI Agents SDK

Create your Vinkius account to connect Fusioo 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 Fusioo with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate workspace records via OpenAI Agents SDK

Your agent needs to interact with Fusioo custom apps using `list_apps` and `get_app_schema` to map out your data structure before making any moves. It knows exactly what fields exist and what types they expect. That context feeds directly into the OpenAI guardrail system when an agent executes `create_app_record` or `update_app_record`. The SDK validates the action against your safety constraints, giving you full visibility into the execution trace on your OpenAI dashboard.

Query custom app data safely

Pulling information out of your workspace requires the `list_app_records` tool to fetch rows of data based on natural language queries. It filters the noise and grabs exactly what the user asked for without manual UI clicks. If the agent needs to verify a specific entry, it fires off `get_record_details` to pull the exact metadata. You can wire this up so a specialized reporting agent handles the read operations while a separate agent handles writes.

Audit teammates and dashboard widgets

Managing access takes time, so your agent runs `list_workspace_users` to pull a complete roster of active teammates. Combine this with the OpenAI tracing tools to log exactly who requested the roster check. The MCP server also exposes `list_dashboard_widgets` and `list_workspace_reports` for auditing your current views. This means your agent reads the current state of your workspace and reports back on what metrics are visible to the team.

Setup guide

Set up Fusioo 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 Fusioo tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fusioo 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="Fusioo Agent",
            instructions="You have access to Fusioo 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 Fusioo. 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 Fusioo 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 Fusioo MCP in OpenAI Agents SDK

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your endpoint URL and pass it to your agent's mcp_servers array. Set cacheToolsList=True to speed up initialization.

Yes. The agent uses list_apps to find the target app and get_app_schema to understand its structure. It then knows exactly how to format requests for that specific database.

No. The SDK handles auto-discovery automatically. Once you attach the MCP Server, the model sees all 12 available tools and decides when to call them.

The server respects standard API throttling rules. If your agent loops and hits a limit, the SDK catches the error. You configure retry logic directly in your Python code.

Your active teammate roster and record metadata remain isolated. The server runs ephemerally in a V8 Isolate Sandbox, meaning data fetched by list_workspace_users is passed straight to your AI client and immediately destroyed on our end. We log nothing.

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