How to Use the Mokaform MCP in OpenAI Agents SDK

Q: How do I register the Mokaform MCP Server inside my OpenAI Agents SDK project?

Install the package using pip install openai-agents first. Then, instantiate MCPServerStreamableHttp with your Vinkius endpoint and pass it to your Agent constructor in the mcpservers list.

Q: Can an OpenAI Agents SDK agent dynamically edit Mokaform questions?

Yes, this is exactly what it does. The agent calls getform to inspect the active layout, processes the user's feedback, and then runs updateform to alter the questions in real time.

Q: Why should I cache the Mokaform tool list in my OpenAI Agents SDK config?

Setting cacheToolsList=True prevents the SDK from making redundant network requests to discover the eight form-building tools on every single turn. This speeds up your agent's response time significantly.

Build production-grade OpenAI Agents SDK systems that build, update, and read dynamic user surveys on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mokaform MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Dynamic Logic Trees inside OpenAI Agents SDK

Your agents can build interactive questionnaires with conditional branching directly through the OpenAI Agents SDK. By invoking `create_form` and `update_form`, the agent designs logic paths that change questions based on what the user answers. This isn't just about static fields. The agent reads the existing structural setup using `get_form` to ensure new questions align perfectly with your existing workspace schema before applying modifications.

Safe Response Processing with Guardrails

Production agents need strict boundaries when handling user data. The MCP Server handles calls to `get_response` and `list_responses`, running them through your safety guardrails to block sensitive personal information before it hits the model. If an agent attempts to purge data using `delete_response`, the SDK validates the operation against your custom security policies. This keeps your survey database clean without risking accidental data loss.

Trace Form Operations on the OpenAI Dashboard

Debugging workspace configurations shouldn't be a guessing game. Every time your agent calls `list_workspaces` or `list_forms` via this MCP Server, the entire payload is tracked inside your OpenAI developer dashboard. You get a clear, step-by-step history of how the agent navigated your forms. If a workspace lookup fails or a form configuration mismatch occurs, you can pinpoint the exact tool call that triggered the issue.

Setup guide

Set up Mokaform 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 Mokaform tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents` first. Then, instantiate `MCPServerStreamableHttp` with your Vinkius endpoint and pass it to your Agent constructor in the `mcp_servers` list.

Yes, this is exactly what it does. The agent calls `get_form` to inspect the active layout, processes the user's feedback, and then runs `update_form` to alter the questions in real time.

Setting `cacheToolsList=True` prevents the SDK from making redundant network requests to discover the eight form-building tools on every single turn. This speeds up your agent's response time significantly.

You can route tasks between specialized agents. For instance, route workspace management tasks to a workspace agent using `list_workspaces`, then hand off to a data agent that queries results via `list_responses`.

Your raw survey responses and form structures stay secure. Vinkius runs the server in an isolated V8 sandbox, meaning your data never leaks to OpenAI's training sets or external logs.

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