How to Use the Formbricks MCP in AutoGen

Let a team of AutoGen agents debate, plan, and manage your Formbricks surveys.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Formbricks MCP to AutoGen

Create your Vinkius account to connect Formbricks to AutoGen 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 Formbricks with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Survey Strategy

This isn't about one agent executing a task. It's about a team of agents collaborating. You can have a "Survey Analyst" agent that uses `list_responses` to find trends, and a "Product Manager" agent that uses `get_survey` to check if the survey is still relevant. They discuss the findings. The analyst might report low scores, and the product manager might suggest a change. This debate leads to a better decision than a single agent could make on its own.

Consensus-Driven Actions

Actions are a result of agreement. After debating, the agents might decide to change a survey. A "Content Writer" agent could propose new text, and an "Operations" agent would be tasked with using `update_survey` to implement the change. With this MCP server, you can even have a "QA" agent that calls `get_survey` after the update to confirm the change was applied correctly. Each agent has a role, and they work together to get the job done right.

Let Agents Run Formbricks

This setup gives your AutoGen agents the keys to Formbricks. They can `create_survey` for a new campaign, `list_contacts` to decide who to target, and `delete_survey` to clean up afterwards. It's full-cycle management through conversation. The real power here is emergent strategy. You don't have to define every step. You define the agents' roles and goals, and they figure out the best way to use the Formbricks tools to achieve them.

Setup guide

Set up Formbricks 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 Formbricks 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="Formbricks_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Formbricks 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="Formbricks_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Formbricks 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 Formbricks. 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 Formbricks 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 Formbricks MCP in AutoGen

You use a helper function to get the Formbricks tools and then pass them to your AssistantAgent's constructor. AutoGen's adapter handles the schema, so your agents can immediately start calling tools like `list_surveys` in their conversations.

Yes, that's a perfect use case for AutoGen. The first agent would call `create_survey`. The second agent would then call `get_survey` using the ID from the first agent's response to check the work before it goes live.

You model roles by creating different agents. For instance, create a "DataAnalystAgent" that only has permission to use read-only tools like `list_responses`, and an "AdminAgent" that can also use `update_survey` or `delete_survey`.

You get decision-making, not just execution. Instead of writing a rigid script, you have agents that can debate the best course of action—whether to update a survey, who to send it to—before acting.

The MCP server ensures each tool call is an isolated, secure transaction. Your AutoGen agents request an action, and our ephemeral instance executes it on Formbricks and returns the result. We don't log or store the contact or survey response data that passes through.

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