How to Use the OpnForm MCP in AutoGen

Q: How do I load OpnForm MCP tools into AutoGen?

Run pip install -U "autogen-extmcp". Use mcpservertools with StreamableHttpServerParams to fetch the tools, then pass them to your AssistantAgent.

Q: Do the agents know which form to update?

They can figure it out. An agent will typically run listforms to find the correct ID before attempting to modify anything.

Q: Is my OpnForm user data safe during agent debates?

Your active session tokens and user profile data from getme never leave the secure Vinkius boundary. The MCP Server operates as a stateless proxy, meaning AutoGen receives the data it requests without anything being stored in transit.

Give your AutoGen multi-agent systems the ability to manage OpnForm workspaces and debate form changes using this MCP Server.

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 AutoGen

Create your Vinkius account to connect OpnForm to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Agent Form Management

The `create_form` tool lets your AutoGen builder agent construct an OpnForm while a reviewer agent checks the schema for excessive fields. Building a complex form requires balancing data collection with user experience. They discuss the structure before anyone touches the API. Once they reach a consensus, the builder executes the MCP tool to deploy the form to your workspace.

Audit Submissions Automatically

The `list_submissions` tool gathers the latest entries on a specific form so you don't have to manually check for spam or invalid file uploads. One agent handles the retrieval. A secondary security agent analyzes those entries. If it finds malicious payloads or junk data, it instructs the first agent to fire `delete_submission` and clean up the database.

Workspace Configuration Control

The `get_me` tool verifies agent identity before they hit `list_workspaces` to see where they have write access. When your agents need context on the current setup, they start here. If an existing form needs a new conditional logic rule, the agents pull the current state with `get_form`. They negotiate the required JSON changes and push the revision using `update_form`.

Setup guide

Set up OpnForm MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes OpnForm tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="OpnForm_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent OpnForm data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="OpnForm_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent OpnForm data")
    print(result.messages[-1].content)

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 AutoGen

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with `StreamableHttpServerParams` to fetch the tools, then pass them to your AssistantAgent.

Yes. You can provide the tool list to specific agents in your conversation. The `McpToolAdapter` automatically converts the schemas so they understand how to use them.

The current MCP Server does not support deleting workspaces. Agents can only remove specific forms using `delete_form` or wipe individual entries via `delete_submission`.

They can figure it out. An agent will typically run `list_forms` to find the correct ID before attempting to modify anything.

Your active session tokens and user profile data from `get_me` never leave the secure Vinkius boundary. The MCP Server operates as a stateless proxy, meaning AutoGen receives the data it requests without anything being stored in transit.

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