How to Use the Voiceflow MCP in Cursor

Q: How do I search with Voiceflow and Cursor?

You query the knowledge base using querykb. The resulting context is then available for the AI to help you write code that correctly references internal documentation.

Q: What state data does this MCP Server expose for Voiceflow and Cursor?

It exposes conversation state through getstate and allows updating it with savestate. This gives your agent the necessary context to make coding decisions based on user input.

Q: Can I review past interactions using Voiceflow and Cursor?

Yes. Use listtranscripts to pull a list of conversation logs, then use gettranscript to grab the full details for debugging your agent's behavior.

Q: Does this MCP Server help with project setup in Voiceflow and Cursor?

The listprojects tool lets you verify all existing agents. You can then use getproject to pull the specific details needed for your integration into a new code module.

Integrate real-time conversational data into Cursor's coding flow with your agent.

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 Cursor

Create your Vinkius account to connect Voiceflow to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Interact with Agents via Code

The `interact` tool lets the AI client send messages directly to a Voiceflow agent. When you run this, it simulates a live user conversation and returns real-time responses that can be injected right into your code base. This capability means you're not working with stubs; you're using genuine API results.

List Available Agents

Start by seeing what exists. Use `list_projects` to get a full list of conversational agents in Voiceflow. Your AI client uses this output to guide which agent needs interaction. Knowing the available projects is the first step before writing any integration code.

Retrieve Knowledge Base Context

Need context for a function? Use `query_kb` against the Voiceflow knowledge base. This tool takes natural language input and returns structured data snippets that you can use to write accurate docstrings or validation logic. It keeps your code grounded in real company documentation.

Setup guide

Set up Voiceflow MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Voiceflow MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Voiceflow transactions." If the MCP tools are loaded correctly, Cursor will call the Voiceflow tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "voiceflow-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

You query the knowledge base using `query_kb`. The resulting context is then available for the AI to help you write code that correctly references internal documentation.

It exposes conversation state through `get_state` and allows updating it with `save_state`. This gives your agent the necessary context to make coding decisions based on user input.

The server handles project definitions, conversation transcripts (`list_transcripts`), and structured variables. This is the core context needed to write functional AI integration code.

Yes. Use `list_transcripts` to pull a list of conversation logs, then use `get_transcript` to grab the full details for debugging your agent's behavior.

The `list_projects` tool lets you verify all existing agents. You can then use `get_project` to pull the specific details needed for your integration into a new code module.

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