How to Use the Voiceflow MCP in VS Code Copilot

Q: How do I search with Voiceflow and VS Code Copilot?

You query the Knowledge Base using querykb. The result is context that can be referenced in code, allowing your team to write functions that rely on internal documentation.

Q: What state data does this MCP Server expose for Voiceflow and VS Code Copilot?

It exposes the conversation state via getstate and allows updates with savestate. This is critical for maintaining accurate user session context across an entire engineering team.

Q: Can I review past interactions using Voiceflow and VS Code Copilot?

Yes. You can use listtranscripts and then pull details with gettranscript. This gives your team a central place to debug agent flows without leaving the IDE.

Q: Does this MCP Server help with project setup in Voiceflow and VS Code Copilot?

The tools provide methods like listprojects and getproject. This enables team-wide, version-controlled management of the agents' configuration.

Standardize conversational agent tools across teams with VS Code Copilot's MCP Server support.

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 VS Code Copilot

Create your Vinkius account to connect Voiceflow to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

List and Verify Agents

The team can use `list_projects` to see every Voiceflow agent available for the codebase. Running this tool ensures everyone on the team is referencing the same set of deployed conversational tools. This centralized view helps prevent developers from accidentally building redundant or outdated agents.

Get Project Metadata

Before writing a single line, use `get_project` to pull all necessary details about a specific Voiceflow agent. This metadata can then be committed into the team's shared configuration files. It makes sure that every developer working on the repo has access to accurate project information.

Manage Conversation Context

The `get_state` and `save_state` tools let your agent read and write user variables. This is essential for multi-step feature development, ensuring that the conversation context persists across different files or modules. It treats the conversational flow like any other piece of state management in a software project.

Setup guide

Set up Voiceflow MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Voiceflow MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Voiceflow tools listed. Try asking: "List my recent Voiceflow transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

You query the Knowledge Base using `query_kb`. The result is context that can be referenced in code, allowing your team to write functions that rely on internal documentation.

It exposes the conversation state via `get_state` and allows updates with `save_state`. This is critical for maintaining accurate user session context across an entire engineering team.

The server handles conversation transcripts, project definitions (`list_projects`), and specific user variables. This ensures the whole team has access to consistent agent information.

Yes. You can use `list_transcripts` and then pull details with `get_transcript`. This gives your team a central place to debug agent flows without leaving the IDE.

The tools provide methods like `list_projects` and `get_project`. This enables team-wide, version-controlled management of the agents' configuration.

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