How to Use the Voiceflow MCP in LlamaIndex

Q: Can I use LlamaIndex to query conversation history?

Yes, absolutely. By retrieving transcripts using listtranscripts and then indexing that data, your agent can answer specific questions about past user interactions based on the indexed text.

Q: What is the best practice for querying Voiceflow's knowledge base with LlamaIndex?

Use querykb. This tool gives you fresh information that LlamaIndex can immediately index. You get answers grounded in the current state of the Knowledge Base, not just what was previously indexed.

Q: Does Voiceflow support multiple projects when using LlamaIndex?

Since listprojects is available, you can build an index covering every single agent. Your client queries this central knowledge store to find information across all defined Voiceflow systems.

Q: If I want to analyze past user conversations, what data type does this MCP Server touch?

The server touches transcripts. You pull these records using the list and get tools, which LlamaIndex then indexes for deep semantic search.

Index Voiceflow data into vector stores with LlamaIndex and your AI client.

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 LlamaIndex

Create your Vinkius account to connect Voiceflow to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Building Knowledge-Augmented RAG Systems

LlamaIndex leverages the `query_kb` tool to pull specific facts from the Voiceflow knowledge base. It takes this live data and indexes it, meaning you can query past API responses or documents for highly accurate answers. You don't just get a random answer; you build a unified index combining external documentation (`list_kb_docs`) with real-time agent data.

State and Project Context Retrieval

Need context to ground your search? Use `get_project` to pull the technical specs of a Voiceflow agent, then index those details. This means your RAG application can answer questions like, 'What is the flow structure for this specific agent?' The `list_projects` tool lets you build an index of *all* available agents, allowing users to query based on project names or categories.

Conversation History Indexing

Instead of just reading a transcript, LlamaIndex indexes it. The `list_transcripts` and `get_transcript` tools allow you to pull entire conversation logs, which are then added to your searchable knowledge base. This means your system can answer questions like, 'What did the user ask about billing last Tuesday?' by querying the indexed historical data.

Setup guide

Set up Voiceflow MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Voiceflow MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Voiceflow tools.",
)
response = await agent.run("List recent Voiceflow data")

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 LlamaIndex

Your AI client uses the server to treat all Voiceflow tools as sources of truth for indexing. It takes structured data—like project details or KB answers—and turns it into semantically searchable vectors.

Yes, absolutely. By retrieving transcripts using `list_transcripts` and then indexing that data, your agent can answer specific questions about past user interactions based on the indexed text.

Use `query_kb`. This tool gives you fresh information that LlamaIndex can immediately index. You get answers grounded in the current state of the Knowledge Base, not just what was previously indexed.

Since `list_projects` is available, you can build an index covering every single agent. Your client queries this central knowledge store to find information across all defined Voiceflow systems.

The server touches `transcripts`. You pull these records using the list and get tools, which LlamaIndex then indexes for deep semantic search.

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