How to Use the Aircall MCP in Pydantic AI

Q: What happens if the Aircall MCP Server returns unexpected data to my Pydantic AI agent?

Your agent will raise a ValidationError. This is the core benefit of Pydantic AI. It prevents your agent from working with malformed or incomplete data, which stops bugs before they start.

Q: Is it difficult to set up the Aircall tools with Pydantic AI?

No, it's straightforward. You import MCPToolset and initialize it with your Vinkius endpoint URL. Then you just pass the toolset to your Agent's constructor. Pydantic AI handles the rest.

Build reliable, type-safe Aircall automations with Pydantic AI, ensuring every API response is validated before your agent uses it.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aircall MCP to Pydantic AI

Create your Vinkius account to connect Aircall 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 Aircall with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Aircall Data, Every Time

This MCP Server works with Pydantic AI to guarantee data integrity. When your agent calls `list_contacts` or `search_contacts`, the JSON response from Aircall is automatically parsed and validated against a Pydantic model. If the API ever returns an unexpected field or a wrong data type, your agent will raise a `ValidationError` immediately. No more silent failures or corrupted data making its way into your system. You can trust the data structures your agent works with.

Execute Actions with Confidence

Pydantic's validation isn't just for reading data. When your agent decides to `create_contact`, Pydantic AI helps ensure the data sent to the Aircall tool is correctly formatted. It's a two-way street for data quality. This strictness means your automations are more predictable and less brittle. You spend less time debugging weird API edge cases and more time building what you actually need. If it runs, it runs correctly.

Use Any LLM for Aircall Phone Ops

Pydantic AI is model-agnostic, and so is this MCP Server. You can use GPT-4, Gemini, Claude, or even a local model running on your machine to drive the agent. The logic for interacting with Aircall remains the same. Your agent can check call logs with `list_calls` or look up user status with `get_user_details`, and you can swap the underlying LLM without rewriting any of your tool-related code. Pydantic AI handles the translation between the model's output and the structured tool call.

Setup guide

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

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

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

It enforces correctness. Every piece of data from the Aircall MCP Server is validated against a strict schema. If the data doesn't match the expected structure, your code fails loudly instead of processing bad data.

Yes. Pydantic AI is model-agnostic. You can configure it to use any LLM, including one running locally, to decide when to call Aircall tools like `list_contacts` or `search_contacts`.

Your agent will raise a `ValidationError`. This is the core benefit of Pydantic AI. It prevents your agent from working with malformed or incomplete data, which stops bugs before they start.

No, it's straightforward. You import `MCPToolset` and initialize it with your Vinkius endpoint URL. Then you just pass the toolset to your `Agent`'s constructor. Pydantic AI handles the rest.

Vinkius handles the connection security. Your requests for call details or user data are sent to a dedicated, single-use sandbox. On top of that, Pydantic AI's validation acts as another security layer, rejecting any data that doesn't conform to the expected schema.

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