How to Use the OpnForm MCP in OpenAI Agents SDK

Q: How do I get my OpenAI agent to use OpnForm?

Just pass the Vinkius server URL to the MCPServerStreamableHttp constructor. The OpenAI Agents SDK automatically discovers all 11 OpnForm tools from the MCP server, so there's no manual mapping needed. Set cacheToolsList=True after the first run to speed things up.

Q: Can my OpenAI agent create conditional logic in OpnForm forms?

Yes. The createform and updateform tools accept the full JSON schema for an OpnForm form, including conditional logic blocks. Your agent can build and manage complex, multi-step forms programmatically.

Q: Is it possible to trace my agent's interactions with OpnForm via the OpenAI Agents SDK?

Absolutely. Every tool call, from listforms to getsubmission, is logged in your OpenAI dashboard. This gives you a complete, auditable trace of how your agent is using the OpnForm API.

Build production agents that manage OpnForm forms and submissions using the safety guardrails of the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect OpnForm MCP to OpenAI Agents SDK

Create your Vinkius account to connect OpnForm to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup OpnForm with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate Form Management Safely

Your agent can now handle the entire form lifecycle. It uses `create_form` to spin up new forms, `update_form` to tweak settings, and `list_forms` to get an inventory of what's active in your workspace. Because you're using the OpenAI Agents SDK, every action is checked against built-in guardrails before it runs. This stops your agent from accidentally running `delete_form` on the wrong ID. It's automation you can actually trust in production.

Process Submissions with Full Traceability

Give your agent the job of processing incoming data. It can pull a queue of new entries with `list_submissions` and then grab individual records using `get_submission` for detailed work. This isn't just a simple API call. The agent framework lets you build specialized agents that hand off tasks. One agent could fetch submissions, while another routes them based on content, all with full execution tracing in your OpenAI dashboard.

A Context-Aware OpnForm MCP Server

This MCP Server exposes tools to interact with your OpnForm account structure. Your agent can identify itself with `get_me` or inspect workspace details with `get_workspace` and `list_workspaces`. This is critical for multi-tenant setups or for agents that need to operate across different projects. They get the context they need to act correctly, without you hardcoding IDs or workspace names.

Setup guide

Set up OpnForm 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 OpnForm tools at runtime.
3

Create your Agent

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

Run the agent

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

Just pass the Vinkius server URL to the `MCPServerStreamableHttp` constructor. The OpenAI Agents SDK automatically discovers all 11 OpnForm tools from the MCP server, so there's no manual mapping needed. Set `cacheToolsList=True` after the first run to speed things up.

Yes. The `create_form` and `update_form` tools accept the full JSON schema for an OpnForm form, including conditional logic blocks. Your agent can build and manage complex, multi-step forms programmatically.

The SDK has built-in guardrails that can prompt a human for confirmation before executing destructive actions. You can configure these policies to prevent an agent from deleting OpnForm submissions or entire forms without approval.

Absolutely. Every tool call, from `list_forms` to `get_submission`, is logged in your OpenAI dashboard. This gives you a complete, auditable trace of how your agent is using the OpnForm API.

This server processes your OpnForm form definitions and submission data. Security is handled at multiple levels: Vinkius provides an ephemeral, zero-trust environment for the server, and the OpenAI SDK provides tracing so you can audit every single action your agent takes on that data.

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