How to Use the JustCall MCP in Pydantic AI

Q: Why use Pydantic AI for JustCall instead of raw requests?

Type safety. When you pull records via listcalls, Pydantic AI guarantees the timestamps and status fields match your Python models before the agent attempts to process them.

Enforce strict runtime validation on JustCall data with Pydantic AI to prevent silent agent failures.

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

Guarantee data via MCP Server

The `justcall-mcp` integrates with Pydantic AI to ensure every API response matches your exact expectations. When your agent calls `get_contact`, the framework validates the returned phone numbers and email addresses against your defined models. The agent fails loudly with a validation error if the upstream API changes a field type. You never end up with silent corruption when parsing `list_messages` or hallucinated delivery statuses in your database.

Audit system integrations safely

This MCP Server pulls active webhook configurations to track your event architecture. Your agent executes `list_webhooks` to audit your integrations. It returns structured lists of endpoint URLs and trigger events. You set this up using the unified MCPToolset approach. The agent verifies which internal systems receive data. Then it maps those connections to internal staff using `list_users` without writing custom HTTP clients.

Investigate call quality

This JustCall integration gives customer support managers reliable access to conversation records. The agent invokes `list_calls` to find inbound interactions with high durations. It then runs `list_recordings` to pull the audio URLs. This framework is model-agnostic. You can swap between Anthropic or local models depending on your budget. The agent uses `list_campaigns` to isolate specific dialer runs while the types always stay safe regardless of the LLM backend.

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-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 with the MCP extra. Initialize an MCPToolset with your HTTP endpoint URL. Pass it to the toolsets array on your Agent.

Type safety. When you pull records via list_calls, Pydantic AI guarantees the timestamps and status fields match your Python models before the agent attempts to process them.

Yes. The framework separates the tool execution from the reasoning engine. You can run list_numbers or get_call using any compatible local model.

The unified MCPToolset supports both Streamable HTTP and SSE transports. Provide the HTTP URL directly to the toolset constructor for this external server.

This integration processes inbound and outbound call duration logs and participant IDs. Connections require a single endpoint token. The runtime executes in an isolated environment that vanishes the moment the connection drops.

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