How to Use the Fieldly MCP in OpenAI Agents SDK

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

Install openai-agents via pip, then instantiate MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this server instance directly into the Agent constructor's mcpservers list to auto-discover all construction tools.

Q: Can the agent check user permissions before calling Fieldly tools?

Yes, your agent can call getme at the start of a session to check the authorized user context before attempting to query sensitive endpoints like listusers or customer billing details.

Run field operations on autopilot with the Fieldly MCP Server connected to your 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 Fieldly MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guardrails for Construction Work Items

Your OpenAI Agents SDK handles the heavy lifting of scheduling and assigning tasks without letting the model go rogue. By declaring the Fieldly MCP Server in your agent stream, the model checks active jobs using `list_work_items` and creates new assignments with `create_work_item` only when strict pre-execution guardrails are met. It's about keeping your field data clean. If an agent attempts to assign a task to an invalid user, the SDK catches the violation before hitting the API. The system validates the parameters against the `list_users` payload, preventing bad assignments and saving your field crew from arriving at the wrong job site.

Multi-Agent Handoffs for Billing

Let specialized agents pass context back and forth instead of relying on a single monolith. A coordination agent can call `list_invoices` to find outstanding balances, then hand the session over to a billing agent that pulls the exact line items using `get_invoice` to draft follow-up emails. Because the OpenAI Agents SDK natively supports clean handoffs, the billing agent never needs access to scheduling tools like `list_bookings`. It stays focused on financial records, while the system records the entire trace on your OpenAI dashboard for immediate debugging.

Auto-Discovered Field Operations via MCP Server

Skip writing manual tool definitions for your construction workflows. When you pass this MCP Server to the SDK constructor, the runtime automatically registers all 11 Fieldly tools so your agent can immediately query `get_booking` or look up parts in `list_articles` without writing a single line of JSON schema. Enabling tool caching ensures that high-frequency calls to `list_customers` do not slow down your live agent runs. The SDK pulls the tool definitions once, letting your agent focus on matching technicians to work orders in real-time.

Setup guide

Set up Fieldly 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 Fieldly tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip, then instantiate `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this server instance directly into the `Agent` constructor's `mcp_servers` list to auto-discover all construction tools.

Yes. You can control tool access at the SDK level by wrapping the server or using agent-specific system instructions to prevent your agent from calling write tools like `create_work_item` while allowing read-only access to `list_bookings`.

The SDK relies on your connection configuration to manage retries. When running high-frequency loops over `list_invoices` or `list_work_items`, enable `cacheToolsList` to minimize overhead and prevent API throttling.

Yes, your agent can call `get_me` at the start of a session to check the authorized user context before attempting to query sensitive endpoints like `list_users` or customer billing details.

Yes. Vinkius runs the server in an isolated sandbox, meaning your raw invoice documents and `get_invoice` payloads are processed ephemerally. The data never trains OpenAI public models and only moves between your secure client and the Fieldly API.

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