How to Use the Typeform MCP in LangChain

Q: How do I get a list of all forms using Typeform and LangChain?

You call listforms to retrieve IDs for every form in the account. The agent then passes these IDs, one by one, to subsequent steps in the chain.

Q: Can I filter responses when using Typeform and LangChain?

Yes. When calling listresponses, you can specify a 'since' date and whether the form was completed or not. This limits the data set your agent needs to process.

Q: What is the best way to manage workspaces with Typeform and LangChain?

Start by using listworkspaces. That function defines the boundaries of your operation, letting your agent know exactly where it should look for forms or responses.

Q: Does this MCP Server support real-time updates with Typeform and LangChain?

Yes. You can use createwebhook to set up a destination URL, which means your chain gets an immediate alert when a form is submitted.

Build multi-step reasoning pipelines for LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Typeform MCP to LangChain

Create your Vinkius account to connect Typeform 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 Typeform with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Discover and analyze form structures

The `list_forms` tool gives your agent a list of all available Typeforms in the account. You can then pass a specific ID to `get_form_details` to pull the exact structure, including every question asked. This lets you build complex chains that don't just collect data, but understand *how* the data was collected. Agents use this structural knowledge to decide which follow-up steps are necessary.

Trace and analyze form responses

Running `list_responses` lets your agent pull all submitted records for a given Typeform. It even supports filtering by date since and completion status, narrowing down the search. This mechanism is key when you need to process historical data in sequence. Your chain can ingest only the responses from the last 24 hours, keeping the reasoning focused.

Map out organizational scope

The `list_workspaces` tool provides a map of all Typeform workspaces available to your agent. From there, you can call `get_workspace_details` to see which forms live in which specific area. This allows your multi-step LangChain process to scope itself correctly before executing any actions. It prevents the agent from wasting time searching across irrelevant collections.

Setup guide

Set up Typeform 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 Typeform 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({
    "typeform-alternative-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 Typeform 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 Typeform. 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 Typeform 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 Typeform MCP in LangChain

You call `list_forms` to retrieve IDs for every form in the account. The agent then passes these IDs, one by one, to subsequent steps in the chain.

Yes. When calling `list_responses`, you can specify a 'since' date and whether the form was completed or not. This limits the data set your agent needs to process.

Start by using `list_workspaces`. That function defines the boundaries of your operation, letting your agent know exactly where it should look for forms or responses.

Yes. You can use `create_webhook` to set up a destination URL, which means your chain gets an immediate alert when a form is submitted.

The server primarily touches collected responses. When you use `list_responses`, the output consists of raw, user-submitted data records which your agent must handle.

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