How to Use the Formbricks MCP in LangChain

Q: Can a LangChain agent create a new Formbricks survey and then read its responses?

Yes, that's exactly what it's for. Your agent would call createsurvey, store the new survey's ID, and then use that ID to call listresponses. This creates a complete feedback loop within a single chain.

Q: What's the best way to handle different Formbricks environments in LangChain?

Use getenvironmentinfo at the start of your chain. This tool tells the agent which Formbricks environment it's connected to. Your agent can then use this information to change its behavior, like using different survey templates for production versus development.

Build feedback pipelines in LangChain by chaining Formbricks API calls to automate survey management.

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 LangChain

Create your Vinkius account to connect Formbricks to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Survey Workflows

This toolset lets your agent run multi-step survey operations. You can build a chain that first runs `list_surveys` to find a specific survey, then uses `list_responses` to pull recent feedback. If a response is negative, the chain can automatically call `get_contact_details` to flag the user for follow-up. The point isn't just calling one tool. It's about connecting them. With LangChain, the output of `get_survey` can directly feed into a decision about whether to `update_survey` or `delete_survey`, letting your agent manage the entire lifecycle programmatically.

Manage Surveys from Agents

Your agent can now create and manage surveys on its own. Give it a goal, and it can use `create_survey` with the right questions. It can then monitor performance by periodically calling `list_responses` and `get_response` for details. This isn't just about reading data. Your LangChain agent gets full write access. It can use `update_survey` to tweak questions on a live survey or `delete_survey` to clean up old experiments, all without manual intervention.

Environment-Aware MCP Server

Your agent isn't flying blind. Before it does anything, it can call `get_environment_info` and `get_product_info` to understand its context. This stops it from running a production survey in a staging environment. It can also pull metadata with `list_tags` to make smarter decisions. For example, an agent could check for a 'Q4-promo' tag before deciding which survey to update, ensuring its actions are relevant to current business goals.

Setup guide

Set up Formbricks MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Formbricks tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "formbricks-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Formbricks transactions"
    })
    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 LangChain

You use the MCP client to get the tools, then pass them to your agent constructor. The client handles turning the Formbricks tools into a format LangChain understands. It's a few lines of code to get started.

Yes, that's exactly what it's for. Your agent would call `create_survey`, store the new survey's ID, and then use that ID to call `list_responses`. This creates a complete feedback loop within a single chain.

Use `get_environment_info` at the start of your chain. This tool tells the agent which Formbricks environment it's connected to. Your agent can then use this information to change its behavior, like using different survey templates for production versus development.

The MCP server handles the auth, boilerplate, and schema definitions for you. You just get a clean list of tools to plug into your agent. You don't have to write and maintain a custom API wrapper.

Yes. The MCP server operates in a zero-trust sandbox and transactions are ephemeral. Your LangChain agent sends a request, the server executes it against Formbricks, and the data—like survey responses or contact info—is passed back without being stored on our end.

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