How to Use the Vapi MCP in Pydantic AI

Q: How do I list all available tools in Vapi with Pydantic AI?

Just call listagenttools. This method shows every single tool the MCP Server makes available, allowing your agent to plan its sequence of actions accurately.

Q: Does Vapi handle complex multi-agent setups with Pydantic AI?

Yep. listsquads lets you list and manage 'squads.' This is how you coordinate multiple specialized agents to tackle a single, large task.

Q: How do I check my recent calls with Vapi and Pydantic AI?

Run listcalls. This gives you a straightforward list of both active and completed voice sessions managed by Vapi, ready for review.

Ensure data correctness with Pydantic AI using the Vapi 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 Vapi MCP to Pydantic AI

Create your Vinkius account to connect Vapi 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 Vapi with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Managing Assistant Personas in Pydantic AI

You set up new Voice AI assistant personas by calling `create_assistant`. This tool requires you to pass a JSON string containing the transcriber, model, and voice details. The data is validated on creation. You can also make changes using `update_assistant`, ensuring your agent's behavior remains type-safe.

Viewing Call Details with the MCP Server

The `get_call_details` tool retrieves call transcripts, metrics, and other data points. Because of Pydantic validation, you know the structure of the returned JSON is correct every single time. Don't forget to check your available resources using `list_phone_numbers`.

Starting Calls via Vapi for Pydantic AI

To start a voice call, use `create_phone_call`, supplying the phone number ID and customer data. The result is guaranteed to fit your defined Python models. Alternatively, you can generate a web link configuration using `create_web_call` for virtual calls.

Setup guide

Set up Vapi 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": {
        "vapi-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Vapi 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 Vapi. 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 Vapi 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 Vapi MCP in Pydantic AI

Just call `list_agent_tools`. This method shows every single tool the MCP Server makes available, allowing your agent to plan its sequence of actions accurately.

Yep. `list_squads` lets you list and manage 'squads.' This is how you coordinate multiple specialized agents to tackle a single, large task.

Vapi tracks call transcripts, metrics, assistant configurations, and phone number usage. The reliability of this data is guaranteed by the MCP Server's validation layer.

Run `list_calls`. This gives you a straightforward list of both active and completed voice sessions managed by Vapi, ready for review.

This server manages Call records, Assistant configurations, Phone numbers, and Transcripts. The strict typing ensures you handle these assets correctly.

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