How to Use the Voiceflow MCP in Windsurf

Q: How do I use Voiceflow and Windsurf together for content retrieval?

You'll start by using querykb. This sends your question to the Knowledge Base, and Cascade reads the result. It handles the fetching and then passes that information along to the rest of your workflow.

Q: Can Voiceflow and Windsurf handle session variable updates?

Yep. You call savestate when you have new data, updating variables for the conversation. If something goes wrong mid-flow, you can always reset everything using deletestate to start clean.

Q: What happens with Voiceflow and Windsurf if I need project details?

The getproject tool pulls all the necessary metadata for a specific agent. Cascade uses this data upfront, ensuring it has context about the limitations or goals of the agent before running any steps.

Q: Does Voiceflow and Windsurf support message sending?

Absolutely. The interact tool lets your autonomous flow send a message back to the Voiceflow agent, simulating a user reply right from your IDE.

Q: What data privacy information can I get about Voiceflow and Windsurf conversations?

You can retrieve the conversation state variables using getstate or pull the full textual history via gettranscript. These tools give you visibility into the user's input and the agent's responses.

Automate complex agent workflows directly within Windsurf.

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 Windsurf

Create your Vinkius account to connect Voiceflow to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Voiceflow projects and knowledge bases.

List all your available agents using `list_projects` to know what you're working with. You can also check the documentation pool by calling `list_kb_docs` or seeing which categories are tagged using `list_kb_tags`. This gives Cascade a full picture of your current conversational assets.

Control conversation flow and session data.

Need to debug an agent's path? Use `get_state` to read the user's variables at any point in time. If you need to reset the context for a new test run, just call `delete_state`. You can also proactively update variable data using `save_state` before Cascade acts.

Analyze and debug conversation history.

After an agent runs, you need to see what was said. Retrieve the full interaction record with `get_transcript`, or check past sessions by listing them out using `list_transcripts`. You can even send a follow-up message right from the workflow using the `interact` tool.

Setup guide

Set up Voiceflow MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Voiceflow MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Voiceflow payment history." If connected, Cascade will call the Voiceflow tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

You'll start by using `query_kb`. This sends your question to the Knowledge Base, and Cascade reads the result. It handles the fetching and then passes that information along to the rest of your workflow.

Yep. You call `save_state` when you have new data, updating variables for the conversation. If something goes wrong mid-flow, you can always reset everything using `delete_state` to start clean.

The `get_project` tool pulls all the necessary metadata for a specific agent. Cascade uses this data upfront, ensuring it has context about the limitations or goals of the agent before running any steps.

Absolutely. The `interact` tool lets your autonomous flow send a message back to the Voiceflow agent, simulating a user reply right from your IDE.

You can retrieve the conversation state variables using `get_state` or pull the full textual history via `get_transcript`. These tools give you visibility into the user's input and the agent's responses.

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