How to Use the Voiceflow MCP in Pydantic AI

Q: How can I perform a structured search using Voiceflow and the Pydantic AI?

You first list available tags with listkbtags to map out your knowledge sources. Then, you use querykb to ask the agent questions, guaranteeing the returned data adheres to defined types.

Q: Is Pydantic AI safe for state management with Voiceflow?

Yes, it is highly reliable. When using savestate, the framework validates the output against your specified models at runtime. You won't get silent data corruption—it’ll fail immediately if something is wrong.

Q: How do I audit chat history with Voiceflow and the Pydantic AI?

Your agent can list transcripts using listtranscripts to see a directory of past chats. Then, you fetch detailed records with gettranscript, ensuring that every piece of data is type-checked upon retrieval.

Build reliable agents with the Pydantic AI and Voiceflow MCP Server.

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 Pydantic AI

Create your Vinkius account to connect Voiceflow to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Conversation Logs

The agent can retrieve full chat histories using `list_transcripts` and then fetch specific details via `get_transcript`. Because of Pydantic's validation, you know exactly what data fields you’re dealing with. This strict type-checking means the conversation data returned is trustworthy; there are no unexpected or missing keys to worry about.

Control State with Type Safety

When an agent needs to save user variables, it uses `save_state`. Critically, this process validates that the data conforms to your expected structure. If the API returns bad data, the agent fails loudly. This built-in validation is perfect for processes where correctness matters more than raw speed.

Structured Knowledge Search

Agents can list searchable document categories using `list_kb_tags`, which helps them understand the scope of available knowledge. They then ask specific questions with `query_kb` to get highly precise answers. This two-step process gives you controlled, validated access to your most important corporate data.

Setup guide

Set up Voiceflow MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "voiceflow-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Voiceflow tools.",
)

result = await agent.run("List recent Voiceflow transactions")
print(result.output)

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 Pydantic AI

You first list available tags with `list_kb_tags` to map out your knowledge sources. Then, you use `query_kb` to ask the agent questions, guaranteeing the returned data adheres to defined types.

Yes, it is highly reliable. When using `save_state`, the framework validates the output against your specified models at runtime. You won't get silent data corruption—it’ll fail immediately if something is wrong.

Your agent can list transcripts using `list_transcripts` to see a directory of past chats. Then, you fetch detailed records with `get_transcript`, ensuring that every piece of data is type-checked upon retrieval.

Yes. The entire point of using this setup is validating state. Every time you call `save_state` or `get_state`, the data integrity is enforced by Pydantic, providing reliable outputs.

This server touches user conversation state variables. This includes structured knowledge base metadata (`list_kb_tags`), session variables, and full chat history records.

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