How to Use the Voiceflow MCP in Mastra AI

Q: How does Mastra AI handle state persistence with Voiceflow?

You use the savestate tool. Your agent client updates user variables, which the MCP Server then commits to the session record. This keeps your multi-step workflow running smoothly over time.

Q: If I need to check existing Voiceflow projects, which tool should I call with Mastra AI?

You must use listprojects. This allows your agent client to verify the existence of a conversation flow before attempting to interact with it.

Q: Does Mastra AI support querying documentation from Voiceflow's knowledge base?

Yes, you call querykb directly through the MCP Server. This provides structured search results that your workflow can then use for decision-making or generating responses.

Q: What tools are available to monitor user interaction in Voiceflow with Mastra AI?

You have gettranscript and listtranscripts. These let your agent client pull the full context of past interactions, which is key for error handling or auditing.

Q: What data privacy information does this MCP Server touch?

This server touches user conversation state/variables and conversation transcripts. Because these are critical to workflow logic, handle them with care.

Build resilient, multi-step business workflows with Mastra AI's agent 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 Mastra AI

Create your Vinkius account to connect Voiceflow to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute complex, conditional logic

Your workflow handles failure gracefully. It uses the MCP Server tools to execute steps that require specific checks—for example, checking if a project exists using `get_project` before proceeding. Because it supports retries and conditional branching, your Mastra AI agent doesn't fail on bad input; it adapts its process flow.

Manage conversation lifecycle

The MCP Server lets you control the entire user experience. You can pull up existing dialogue history with `list_transcripts` or reset a session completely by calling `delete_state`. This ensures clean, predictable interactions. Furthermore, tools like `get_state` let your workflow pause and check exactly what variables are set before moving to the next step.

Query structured knowledge bases

Don't just ask a question; get specific data. The MCP Server provides `query_kb` for searching, but it also lets you list available documents (`list_kb_docs`) and the categories they belong to (`list_kb_tags`). This structure means your workflow knows exactly where to look before attempting an action.

Setup guide

Set up Voiceflow MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Voiceflow tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "voiceflow-mcp-client",
  servers: {
    "voiceflow-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Voiceflow Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Voiceflow tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Voiceflow transactions"
);
console.log(result.text);

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 Mastra AI

You use the `save_state` tool. Your agent client updates user variables, which the MCP Server then commits to the session record. This keeps your multi-step workflow running smoothly over time.

You must use `list_projects`. This allows your agent client to verify the existence of a conversation flow before attempting to interact with it.

Yes, you call `query_kb` directly through the MCP Server. This provides structured search results that your workflow can then use for decision-making or generating responses.

You have `get_transcript` and `list_transcripts`. These let your agent client pull the full context of past interactions, which is key for error handling or auditing.

This server touches *user conversation state/variables* and *conversation transcripts*. Because these are critical to workflow logic, handle them with care.

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