How do I find the Workspace ID for my Flow account?

You can use the 'list_workspaces' tool. The agent will retrieve all workspaces you have access to and return their names and unique IDs, which you can then use for other operations.

Can I mark a task as completed using the agent?

Yes! Use the 'update_task' tool, provide the Task ID, and set the 'status' parameter to 'completed'. The task will be immediately updated in Flow.

How do I see the discussion history for a task?

Use the 'list_task_comments' tool and provide the Task ID. The agent will retrieve all messages and replies associated with that task, allowing you to catch up on the discussion.

Flow MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes

Name: Flow
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Flow through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Flow Assistant",
            instructions=(
                "You help users interact with Flow. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Flow"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Flow MCP Server

Connect your Flow account to any AI agent and automate your project management and team collaboration through the Model Context Protocol (MCP). Flow (getflow.com) provides a clean and powerful platform for organizing work, tracking task progress, and facilitating team discussions. Now, you can manage your workspaces, projects, and individual tasks directly through natural conversation.

The OpenAI Agents SDK auto-discovers all 12 tools from Flow through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Flow, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Project Coordination — List all projects within your workspaces and retrieve detailed metadata, including ownership and due dates.
Task Management — Create, update, and list tasks across workspaces, projects, or specific task lists. Change statuses (incomplete/completed) instantly.
Organized Lists — Access and list task groups (Lists) within projects to maintain a clear hierarchy of work.
Team Interaction — List all workspace members and teams, and participate in task discussions by reading or adding comments.
Workspace Oversight — Get a high-level view of all the top-level workspaces you belong to.
Real-time Updates — Fetch specific task details or metadata to keep your team informed and your projects on track.

The Flow MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Flow to OpenAI Agents SDK via MCP

Follow these steps to integrate the Flow MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from Flow

Why Use OpenAI Agents SDK with the Flow MCP Server

OpenAI Agents SDK provides unique advantages when paired with Flow through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Flow + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Flow MCP Server delivers measurable value.

Automated workflows: build agents that query Flow, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Flow, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Flow tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Flow to resolve tickets, look up records, and update statuses without human intervention

Flow MCP Tools for OpenAI Agents SDK (12)

These 12 tools become available when you connect Flow to OpenAI Agents SDK via MCP:

add_task_comment

create_task

Create a new task

get_project

Get project details

get_task

Get task details

list_projects

List projects in workspace

list_task_comments

List task discussions

list_task_lists

List lists in project

list_tasks

List tasks

list_workspace_members

List team members

list_workspace_teams

List workspace teams

list_workspaces

List top-level workspaces

update_task

). Update an existing task

Example Prompts for Flow in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Flow immediately.

"List all my Flow projects in the 'Marketing' workspace."

"Create a new task: 'Review final design mockup' in the 'Design' list."

"Add a comment to task 'task_123': 'Design looks great, proceed to coding'."

Troubleshooting Flow MCP Server with OpenAI Agents SDK

Common issues when connecting Flow to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Flow + OpenAI Agents SDK FAQ

Common questions about integrating Flow MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.