How to Use the Voiceflow MCP in Google ADK

Q: How do I list knowledge sources using Voiceflow and the Google ADK?

You use listkbtags to see what types of documents exist in your knowledge base. This provides a structured overview, telling your agent exactly where its information comes from.

Q: Can I manage conversation history with Voiceflow and the Google ADK?

Yes. The listtranscripts tool lets you pull a list of all recorded conversations. Your agents can then access specifics using gettranscript, providing full audit capabilities.

Q: What is the best way to handle session state with Voiceflow and the Google ADK?

You use savestate when an agent needs to commit current user variables. Conversely, if a major workflow change occurs, deletestate ensures that old context doesn't accidentally bleed into new interactions.

Q: Does Voiceflow support project discovery with the Google ADK?

It does. The listprojects tool allows your agent to query and identify every single voiceflow project available in your system, making multi-system integration straightforward.

Build enterprise agents using the Google ADK and Voiceflow MCP Server.

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 Google ADK

Create your Vinkius account to connect Voiceflow to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Discover Available Projects

Your agent starts by listing all available voiceflow projects with `list_projects`. After finding a project ID, it can pull specific details using `get_project`. This capability is key for enterprise setups where agents must know which systems they have access to. It prevents the agent from guessing or needing manual configuration.

Optimize User Feedback Loops

Agents monitor user satisfaction by retrieving feedback data with `get_feedback`. If a session is concluded, it can reset variables and clear the context using `delete_state`. This makes your agent highly adaptive. By tracking feedback and resetting state when necessary, you ensure that every new interaction starts clean.

List Structured Resources

The server helps agents catalogue knowledge resources by listing available tags (`list_kb_tags`) or retrieving a history of chats using `list_transcripts`. This provides the agent with metadata about its entire operational scope. It also gives visibility into past conversations, helping your agent understand user patterns from previous sessions.

Setup guide

Set up Voiceflow MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Voiceflow tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Voiceflow_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Voiceflow tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You use `list_kb_tags` to see what types of documents exist in your knowledge base. This provides a structured overview, telling your agent exactly where its information comes from.

Yes. The `list_transcripts` tool lets you pull a list of all recorded conversations. Your agents can then access specifics using `get_transcript`, providing full audit capabilities.

You use `save_state` when an agent needs to commit current user variables. Conversely, if a major workflow change occurs, `delete_state` ensures that old context doesn't accidentally bleed into new interactions.

It does. The `list_projects` tool allows your agent to query and identify every single voiceflow project available in your system, making multi-system integration straightforward.

This server touches user conversation state variables. This includes chat transcripts, specific voiceflow project identifiers (`get_project`), and general user feedback metadata.

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