How to Use the FlowUs MCP in OpenAI Agents SDK

Q: How do I connect the FlowUs MCP Server to the OpenAI Agents SDK?

Install openai-agents and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this instance directly into the Agent constructor's mcpservers list to enable auto-discovery.

Q: How does OpenAI Agents SDK handle schema mismatches in FlowUs?

The agent runs getdatabase to fetch the schema before attempting to write. If the agent tries to call createdatabaserow with invalid fields, your validation layer catches the error before the API request is made.

Q: Does this server support caching for fast agent execution?

Yes. Set cacheToolsList=True in your SDK initialization to avoid fetching the tool definitions on every turn, which speeds up your agent's response time when calling listblocks via the MCP.

Run production-ready OpenAI Agents SDK workflows that directly modify your FlowUs workspaces with built-in execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FlowUs MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe database writes with OpenAI Agents SDK

This MCP Server exposes `create_database_row` to let your OpenAI agents append structured records directly into FlowUs. Your production Python code controls this process by validating the agent's intent before the API call executes. By using `query_database` alongside `get_database`, your agent inspects the target schema to prevent malformed entries. The OpenAI dashboard traces every single database interaction, so you see exactly what the agent tried to write.

Multi-agent wiki updates and page creation

Your specialized agents coordinate to build documentation by calling `create_page` and `update_page` in a structured pipeline. One agent gathers technical logs while another formats the output into clean workspace documents. You manage these handoffs natively using the OpenAI Agents SDK context manager, which handles the underlying HTTP transport of the MCP Server. The agent reads the existing layout with `list_blocks` before making any modifications, keeping your wiki organized.

Workspace user audits and access checks

Your agent monitors team access by executing `list_users` and cross-referencing active accounts against your internal database. The MCP context helps the agent monitor directories without manual JSON schema declarations. The agent lists all available directories via `list_pages` to verify that sensitive pages restrict unauthorized views. If a compliance issue pops up, the system logs the event directly to your OpenAI observability dashboard.

Setup guide

Set up FlowUs 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 FlowUs tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this instance directly into the `Agent` constructor's `mcp_servers` list to enable auto-discovery.

Yes, you configure guardrails within the SDK to intercept tool calls before they hit the server. This prevents the agent from running write operations like `update_page` while still allowing read-only actions like `get_page`.

The agent runs `get_database` to fetch the schema before attempting to write. If the agent tries to call `create_database_row` with invalid fields, your validation layer catches the error before the API request is made.

Yes. Set `cacheToolsList=True` in your SDK initialization to avoid fetching the tool definitions on every turn, which speeds up your agent's response time when calling `list_blocks` via the MCP.

Your block text and page content are processed in memory during active tool execution. The server never stores your raw database rows, using end-to-end TLS encryption to pass data directly to your OpenAI runtime.

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