How to Use the JustCall MCP in Pydantic AI

Q: How do I configure JustCall with Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCP Server toolset with your Vinkius HTTP endpoint. Pass this toolset into your Agent definition.

Q: Why does Pydantic AI reject some JustCall responses?

If the agent hallucinates an argument for getcontact, Pydantic throws a validation error immediately. The framework forces the model to correct its inputs before executing the tool.

Type-safe JustCall integration for Pydantic AI agents that demand strict validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JustCall MCP to Pydantic AI

Create your Vinkius account to connect JustCall 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 JustCall with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI validation for call data

Your agent fetches communication records using `list_calls` and `get_call_details`. Because this is Pydantic AI, every JSON response from the JustCall MCP Server gets validated against your predefined models. If the API returns a string instead of an integer for call duration, the execution fails loudly. You never deal with silent data corruption. The agent knows exactly what shape the data takes. When it reads `get_message_details`, you guarantee the payload matches your schema before the agent attempts to write that data to your local database.

Type-safe outbound messaging

The `send_message` tool requires precise inputs to work correctly. You define the exact structure for the destination number and message body. The agent constructs the request, and Pydantic catches any missing fields before the HTTP call ever leaves your machine. You verify your sending numbers first. The agent calls `list_account_numbers` to ensure the outbound line actually exists. The MCP Server executes the request, preventing failed deliveries and keeping your application logic predictable.

Predictable contact management

Your agent uses `create_contact` to push new leads into the system with exact field mappings. Pydantic guarantees that the phone number format and name strings match JustCall's requirements, stopping API errors at the source. You sync your internal systems by reading `list_contacts` and `list_team_users`. The agent pulls the active user list, validates the response, and updates your local state. You build reliable synchronization scripts that refuse to process malformed data.

Setup guide

Set up JustCall 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": {
        "justcall-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]`. Initialize an MCP Server toolset with your Vinkius HTTP endpoint. Pass this toolset into your Agent definition.

If the agent hallucinates an argument for `get_contact`, Pydantic throws a validation error immediately. The framework forces the model to correct its inputs before executing the tool.

Yes, the framework supports both Streamable HTTP and SSE transports. You connect to the external Vinkius server and the tools execute asynchronously.

The framework is completely model-agnostic. You can switch from Claude to a local Llama model, and the agent will still use `list_messages` the exact same way.

Vinkius manages authentication at the edge. When your agent pulls sensitive SMS texts via `list_messages`, the traffic passes through a temporary sandbox. No message content is ever stored on the middle layer, ensuring strict data compliance.

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