How to Use the Voiceflow MCP in LangChain

Q: If I use LangChain with this server, can I manage conversation history?

Absolutely. The getstate tool retrieves the current user session data. You can also use savestate to update variables, making sure your agent retains context across different steps in a long-running chain.

Q: What is the best way to query Voiceflow's knowledge base using LangChain?

The dedicated querykb tool handles this. Your client sends a question, and the server returns specific, relevant answers from the Knowledge Base, letting your agent synthesize accurate responses.

Q: Does Voiceflow support multiple projects when using LangChain?

Yes. The listprojects tool lets you see all available Voiceflow projects. Your client can then use getproject to target and work with a specific agent's details.

Q: If I want to analyze past user conversations, what data type does this MCP Server touch?

The server touches transcripts. Using tools like listtranscripts lets your LangChain chain access and process records of previous chat sessions for analysis.

Build multi-step conversational chains with your AI client and the LangChain framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Voiceflow MCP to LangChain

Create your Vinkius account to connect Voiceflow 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 Voiceflow with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Reasoning Chains

The `interact` tool lets your agent send messages to Voiceflow, treating each exchange as a step in a complex reasoning chain. The output of that message becomes the input for the next tool call, letting you build deep conversation logic. You can also manage the session state using `get_state` and `save_state`. This gives your multi-step agent persistent memory, so it remembers what was said earlier in the chat.

Knowledge Base Interaction

Need an answer from Voiceflow's knowledge base? The `query_kb` tool executes a search against the documentation. It pulls specific answers that your agent can then use to respond, grounding its reply in actual content. Beyond querying, you can list available topics using `list_kb_docs`. This lets your LangChain chain first figure out what knowledge areas exist before it even asks a question.

Project and Transcript Management

Getting project context is key. Use the `get_project` tool to pull detailed info about the Voiceflow agent itself. Your client can then use this data to inform how it should behave or what options it should present. Furthermore, the `list_transcripts` and `get_transcript` tools let your chain analyze past conversations. This is perfect for building agents that audit previous interactions.

Setup guide

Set up Voiceflow 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 Voiceflow 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({
    "voiceflow-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 Voiceflow 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 Voiceflow. 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 Voiceflow 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 Voiceflow MCP in LangChain

Your AI client uses the MCP Server to treat every Voiceflow action like a function call. This allows you to chain together multiple tools—like getting state, querying KB, and then sending an interaction message—into one cohesive process.

Absolutely. The `get_state` tool retrieves the current user session data. You can also use `save_state` to update variables, making sure your agent retains context across different steps in a long-running chain.

The dedicated `query_kb` tool handles this. Your client sends a question, and the server returns specific, relevant answers from the Knowledge Base, letting your agent synthesize accurate responses.

Yes. The `list_projects` tool lets you see all available Voiceflow projects. Your client can then use `get_project` to target and work with a specific agent's details.

The server touches `transcripts`. Using tools like `list_transcripts` lets your LangChain chain access and process records of previous chat sessions for analysis.

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