How to Use the Float MCP in OpenAI Agents SDK

Q: Does the OpenAI Agents SDK support caching for Float resources?

Setting cacheToolsList=True in your server configuration prevents redundant schema lookups. This keeps your execution loops fast when your agent repeatedly queries listpeople or getperson.

Q: How do I handle scheduling conflicts with this MCP Server?

Your Python agent should first call listallocations to check for overlapping blocks. If a conflict exists, the agent can run custom logic to find an open slot before calling createallocation.

Let your OpenAI Agents SDK build accurate schedules and manage team capacity directly inside your production agent workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Float MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate task assignments via OpenAI Agents SDK

`create_allocation` lets your OpenAI agent assign tasks to developers based on actual availability. By feeding current team workloads straight into your run loop, you stop double-booking people before it happens. The SDK handles the heavy lifting by auto-discovering this MCP tool inside your agent's execution context. You get clean trace logs on the OpenAI dashboard every time an allocation is written or modified.

Audit team hours with built-in guardrails

`get_logged_time` retrieves real hours worked so your agent can verify project budgets against actuals. You set validation rules inside your python code to block the agent from pulling massive datasets that hit rate limits. OpenAI's guardrails ensure the agent only queries specific time logs during a run. This setup prevents runaway loops from making useless API calls when checking team metrics.

Sync time off before scheduling with this MCP Server

`list_time_offs` exposes developer vacation schedules to prevent your agent from booking unavailable staff. Your system reads these dates before making any scheduling decisions. Using the async context manager in python, your agent checks these records in parallel with active project tasks via the MCP Server. It keeps your resource calendar accurate without manual data entry.

Setup guide

Set up Float 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 Float tools at runtime.
3

Create your Agent

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

Run the agent

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

Pass your Vinkius HTTP endpoint token into the MCPServerStreamableHttpParams constructor. The SDK manages bearer tokens under the hood, letting your agent safely call `list_projects` without exposing raw credentials.

Yes, you control this by defining specific agent schemas in Python. If you only want an agent to read data, expose `list_allocations` but omit `create_allocation` from the tool list.

Setting `cacheToolsList=True` in your server configuration prevents redundant schema lookups. This keeps your execution loops fast when your agent repeatedly queries `list_people` or `get_person`.

Your Python agent should first call `list_allocations` to check for overlapping blocks. If a conflict exists, the agent can run custom logic to find an open slot before calling `create_allocation`.

All Float scheduling data, including logged hours and holiday schedules, remains inside a secure V8 sandbox. Vinkius processes these payloads ephemerally, meaning your team's tracking metrics are never stored on external 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