How to Use the Callpicker MCP in Pydantic AI

Q: How do I add Callpicker tools to a Pydantic AI agent?

First, pip install "pydantic-ai-slimmcp". Then create an MCPToolset instance with your Vinkius URL and pass it into the toolsets list when you initialize your agent.

Q: What happens if the Callpicker API returns an unexpected field when using Pydantic AI?

Your agent will immediately raise a ValidationError. This is a core feature, preventing your code from processing malformed data and protecting your application from silent failures.

Build type-safe, reliable agents with Pydantic AI that interact with your phone system and never fail silently.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Callpicker MCP to Pydantic AI

Create your Vinkius account to connect Callpicker 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 Callpicker with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Guaranteed Correct Call Data

Pydantic AI's whole point is correctness. When your agent calls `get_call_details` or `list_call_logs`, the JSON response is immediately parsed and validated against a Pydantic model. If a field is missing, has the wrong type, or is just plain junk, your code will raise a `ValidationError`. This means no more defensive coding or silent data corruption. You can trust that the call log data your agent is working with matches the exact schema you expect. If the upstream API ever changes without warning, your agent fails loud and clear, which is exactly what you want in production.

Model-Agnostic Phone Operations

With Pydantic AI, your choice of LLM doesn't lock you in. You can use the Callpicker tools with an agent powered by GPT-4, Gemini, Claude, or even a local model running on your own machine. The logic for using `make_call` or `get_recording_url` is completely separate from the model provider. This gives you the freedom to swap out the 'brain' of your agent without rewriting all the tool-handling code. If a new, better model comes out tomorrow, you can switch to it and your Callpicker integration will keep working just as it did before.

Reliable PBX System Checks with Pydantic AI

When you're checking on critical infrastructure, you need to trust the data you're getting. An agent using Pydantic AI can call `get_pbx_system_status` or `list_pbx_extensions` and know for certain that the response is well-formed. No guesswork involved. This is especially important for automated monitoring and remediation. If an agent gets a malformed status response, it won't try to act on bad data. The validation layer ensures that any decisions—like whether to send an alert or reroute numbers—are based on a known, valid system state. This MCP Server gives your type-safe agent the tools it needs.

Setup guide

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

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

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

First, `pip install "pydantic-ai-slim[mcp]"`. Then create an `MCPToolset` instance with your Vinkius URL and pass it into the `toolsets` list when you initialize your agent.

Your agent will immediately raise a `ValidationError`. This is a core feature, preventing your code from processing malformed data and protecting your application from silent failures.

Yes. Pydantic AI is model-agnostic. You can connect the Callpicker MCP Server to an agent running any compatible LLM, whether it's local, open-source, or a commercial API.

Before your agent code ever sees the data, Pydantic AI validates every single record from the report against a predefined Pydantic model. If any part of the data doesn't match the expected schema, it fails instead of letting bad data through.

Vinkius executes every request in a dedicated, single-use sandbox. The server only handles the transaction of call metadata like logs or recording URLs; it has no access to or persistence of the underlying audio content.

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