How to Use the CallRail MCP in Pydantic AI

Q: How do I use CallRail tools with a Pydantic AI agent?

Install pydantic-ai-slimmcp and create an MCPToolset instance with your Vinkius URL. Add that toolset to your Agent constructor, and Pydantic AI will generate typed functions for all the CallRail operations.

Q: Can I use Pydantic AI to get a list of all my CallRail trackers?

Yes. Once connected, your agent can call the listtrackers tool. The result will be a list of Pydantic objects, each representing one of your tracking numbers and its associated source, all fully typed and validated.

Add type-safe access to your CallRail account from any Python agent with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallRail MCP to Pydantic AI

Create your Vinkius account to connect CallRail 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 CallRail with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get CallRail data you can actually trust

This setup is all about correctness. When your agent calls `list_calls` or `get_call_details`, Pydantic AI automatically validates the API response against a strict, predefined schema. You get clean data objects to work with. If CallRail's API ever returns a malformed field, an unexpected null, or a data type mismatch, your code will raise a `ValidationError` immediately. This prevents silent data corruption and makes your agent far more reliable. You'll know the instant the data isn't what you expect.

Interact with your account using clean objects

Stop parsing messy JSON dictionaries in your agent code. With this MCP Server, Pydantic AI gives you structured Python objects for every API call. The output of `list_companies` is a list of `Company` objects, not a blob of text. This makes your agent's internal logic much cleaner and easier to maintain. You get IDE autocompletion for fields, and your code is less likely to break if the API adds new, optional attributes. It forces a level of discipline that pays off.

Build a reliable CallRail agent with any LLM

Pydantic AI is model-agnostic, so you're not locked into one provider. You can use this server to connect CallRail to an agent powered by OpenAI, Anthropic, Gemini, or even a model running on your own machine. The tool-calling and data validation work the same way regardless of the backend LLM. This gives you the freedom to choose the right model for the job without having to rewrite all your data handling logic. The correctness guarantees come from Pydantic, not the model.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and create an `MCPToolset` instance with your Vinkius URL. Add that toolset to your `Agent` constructor, and Pydantic AI will generate typed functions for all the CallRail operations.

If the API returns data that doesn't match the expected Pydantic models, your Pydantic AI agent will raise a `ValidationError`. This is a feature, not a bug—it prevents your agent from working with corrupted or unexpected data.

Yes. Once connected, your agent can call the `list_trackers` tool. The result will be a list of Pydantic objects, each representing one of your tracking numbers and its associated source, all fully typed and validated.

The validation adds a tiny bit of overhead, but it's usually negligible compared to the network latency of the API call itself. For most agentic workflows, the reliability gains from type safety are well worth the small performance cost.

It's only ever in memory for the duration of a request. Your Pydantic AI agent asks for data, the MCP server gets it from CallRail, validates it, and streams it back. Nothing is written to disk or logged on the server.

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