Voiceflow Connector for AI agents.
12 live capabilities
Manage and test conversational bots using natural language.
Waiting for input…
Why people use Voiceflow
Fix Voiceflow Bot Debugging with the Voiceflow
With this Connector, you can just ask your agent to do the heavy lifting. You can pull transcripts, check conversation states, or query your knowledge base without ever leaving your chat. You get a direct line of command to your bot's data, which cuts out the manual navigation entirely.
What Vinkius changes
You get a direct line of command to your Voiceflow projects from your chat interface.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Debugging a looping flow
A designer notices a bot is stuck.
- Real-world use case 02
RAG verification
A developer wants to see if a document was indexed.
- Real-world use case 03
User sentiment analysis
A product manager wants to see if a new flow is liked.
Complete set · 12capabilities
The complete Voiceflow capability set.
These are the exact actions your AI can choose when you ask it to work with Voiceflow.
01—04
4 capabilities in this set.
Part of 12 available through Voiceflow.
- 01 Capability
Get state
Check the current variables and conversation state for a user. It's perfect for seeing exactly where a user is stuck in a flow.
- 02 Capability
Get transcript
Pull the full details of a specific conversation. Use it to read the exact back-and-forth between a user and the bot.
- 03 Capability
Interact
Send a message to your Voiceflow agent. This lets you test responses and trigger actions instantly from your chat.
- 04 Capability
List kb docs
See all the documents currently in your knowledge base. Use it to verify that your RAG data is loaded correctly.
05—08
4 capabilities in this set.
Part of 12 available through Voiceflow.
- 05 Capability
List transcripts
Get a list of all conversation transcripts. Use this to find specific sessions for review.
- 06 Capability
Save state
Update or set user variables and conversation states. Use this to manually move a user through a flow or set specific data.
- 07 Capability
Query kb
Ask a question directly to your Knowledge Base. It lets you see what the bot knows without having to run a full test.
- 08 Capability
List kb tags
See all the tags applied to your knowledge base documents. Use it to organize and find specific content types.
09—12
4 capabilities in this set.
Part of 12 available through Voiceflow.
- 09 Capability
List projects
See a list of all your Voiceflow projects. This makes it easy to switch between different bots you're managing.
- 10 Capability
Delete state
Reset a user's conversation state. This is the fastest way to clear a session and start a test from scratch.
- 11 Capability
Get feedback
Pull user upvotes and downvotes. This helps you see what parts of the conversation are actually working for people.
- 12 Capability
Get project
Get the specific details for a Voiceflow project. Use this to quickly check your current configuration settings.
Set up in minutes
One URL. Then ask Voiceflow to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Voiceflow from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_l22Y6YFkjLlbfmb2bwNvq56Y3lGMb9ioSh3t5jM5/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Voiceflow, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Voiceflow for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_l22Y6YFkjLlbfmb2bwNvq56Y3lGMb9ioSh3t5jM5/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Voiceflow URL.
- Step 03
Save and start
Save the connection and enable Voiceflow in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"voiceflow": {
"url": "https://edge.vinkius.com/vk_preview_l22Y6YFkjLlbfmb2bwNvq56Y3lGMb9ioSh3t5jM5/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Voiceflow
Open Agent mode in chat and ask: "Using Voiceflow, help me...". 12 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"voiceflow": {
"url": "https://edge.vinkius.com/vk_preview_l22Y6YFkjLlbfmb2bwNvq56Y3lGMb9ioSh3t5jM5/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Voiceflow
Ask Copilot: "Using Voiceflow, help me...". 12 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"voiceflow": {
"url": "https://edge.vinkius.com/vk_preview_l22Y6YFkjLlbfmb2bwNvq56Y3lGMb9ioSh3t5jM5/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Voiceflow
Open Cascade and ask: "Using Voiceflow, help me...". 12 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"voiceflow": {
"url": "https://edge.vinkius.com/vk_preview_l22Y6YFkjLlbfmb2bwNvq56Y3lGMb9ioSh3t5jM5/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Voiceflow
Ask Cline: "Using Voiceflow, help me...". 12 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add voiceflow --transport http "https://edge.vinkius.com/vk_preview_l22Y6YFkjLlbfmb2bwNvq56Y3lGMb9ioSh3t5jM5/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Voiceflow
Ask Claude: "Using Voiceflow, show me...". 12 tools are ready
Where the request belongs
Work Voiceflow can move forward.
This is for the conversation designer who's tired of manual testing and the AI developer who needs to debug complex logic without hunting through dashboards.
Conversation Designer
Tests agent responses and queries the knowledge base via simple commands during the prototyping phase.
AI Developer
Inspects transcripts and debugs user states to fix broken flows and logic errors quickly.
Product Manager
Monitors user feedback and conversation logs to see how the bot is performing in the wild.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsFlowiseAI
Build LLM orchestration flows visually with a drag-and-drop interface for creating AI chatbots, agents, and RAG pipelines.
Chaindesk
Build no-code AI agents trained on your own data that handle customer support, lead qualification, and FAQ resolution.
GPTBots
Manage your conversational AI agents, workflows, and knowledge bases via AI.
Tencent Yuanqi
Orchestrate Tencent Yuanqi AI Agents. manage assistants, trigger conversations, and handle RAG documents directly from any AI agent.
ChatBot.com
Manage conversational AI and bot workflows via ChatBot. track stories, interactions, and user data directly from any AI agent.
Dify
Manage agentic workflows via Dify. send chat messages, track conversations, audit app parameters, and handle file uploads directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Voiceflow connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Voiceflow.
The practical details behind the request, access and result.
How can I use the Voiceflow MCP to test my chatbot?
You can send messages directly to your bot through your AI client to see how it responds in real-time. This lets you test complex flows and triggers without having to manually click through the builder.
Can I check my Voiceflow Knowledge Base with this Connector?
Yes, you can ask your AI agent to query your Knowledge Base directly. This helps you verify that your RAG data is accurate and that the bot is pulling the correct information.
How does the Voiceflow MCP help with debugging?
It gives you direct access to conversation states and transcripts. You can see exactly where a user got stuck or check the variables at any point in the flow to find and fix logic errors quickly.
Can I see user feedback through the Voiceflow MCP?
You can pull user upvotes and downvotes directly into your chat. This makes it much easier to monitor how real people are interacting with your bot and identify areas that need improvement.
Is the Voiceflow MCP good for managing multiple bots?
Yes, it lets you list all your projects and quickly switch between them. You can manage your entire conversational ecosystem from one place instead of opening multiple tabs.
Can I reset a user session using the Voiceflow MCP?
You can use the Connector to clear a user's conversation state. This is great for testing because it lets you start a fresh session with a single command.
Does the Voiceflow MCP work with Claude and Cursor?
Yes, it works with any MCP-compatible client, including Claude, Cursor, and Windsurf. You just need your Voiceflow API key to get started.
Can I query my Voiceflow Knowledge Base directly via AI?
Yes! Use the query_kb capability with your question. Your agent will trigger the Voiceflow RAG system and return the answer based on your uploaded documents.
How do I see the transcripts for a specific project?
Run the list_transcripts query with your Project ID. The agent will return a list of past conversation logs, which you can then inspect using get_transcript.
Is it possible to reset a user's session via AI?
Absolutely. Use the delete_state capability and provide the User ID. This will permanently clear the conversation history and variables for that specific session.
One connection away
Give your agent a direct line to Voiceflow.
Connect Voiceflow once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available