How to Use the Vibrato MCP in Pydantic AI

Q: How does Vibrato ensure data quality with Pydantic AI?

Every time your agent calls a tool like getcallstatus, the response is validated against Pydantic models. This means you get guaranteed, structured data every single time.

Q: Can I use Vibrato for call initiation with Pydantic AI?

Yes. When calling createcall or createcallfromtemplate, the resulting metadata is immediately typed and validated, giving you clean data to work with.

Q: What if I need to list calls with Vibrato and Pydantic AI?

You use listcalls. The returned list adheres strictly to a schema you define. This means your agent knows exactly what fields it's getting, eliminating guesswork.

Ensure perfect data structure from phone calls with your Pydantic 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 Vibrato MCP to Pydantic AI

Create your Vinkius account to connect Vibrato 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 Vibrato with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate new call metadata.

When you execute `create_call`, the agent gets back a response that is forced into a defined schema. If the API returns unexpected data, your agent fails loudly with an error, not silent garbage. This guarantees that the prompt, phone number, and locale fields always match what you expect.

Structure call template execution.

Using `create_call_from_template` means the output is predictable. The agent receives a clean object detailing the initiated call's ID and status. This eliminates the risk of processing malformed or incomplete conversation records.

Validate call history records.

Whether you use `list_calls` or check status with `get_call_status`, the response is validated against your Pydantic model. You don't have to guess what data fields exist. If a field is missing, the agent throws an error immediately. Correctness over everything.

Setup guide

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

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

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

Every time your agent calls a tool like `get_call_status`, the response is validated against Pydantic models. This means you get guaranteed, structured data every single time.

Yes. When calling `create_call` or `create_call_from_template`, the resulting metadata is immediately typed and validated, giving you clean data to work with.

This server touches call status, template names, and contact details. Because of your framework's validation, these fields are always represented by predictable Python types.

You use `list_calls`. The returned list adheres strictly to a schema you define. This means your agent knows exactly what fields it's getting, eliminating guesswork.

The server handles call status information. Because of runtime validation, you can be sure that only correctly structured records are passed to your agent's internal logic.

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