How to Use the CallFire MCP in Pydantic AI

Q: How do I load CallFire into Pydantic AI?

Instantiate an MCPToolset pointing to your Vinkius HTTP endpoint. Pass this into the toolsets array when defining your Agent. Do not use the deprecated MCPServerHTTP class.

Type-safe voice and SMS execution. Connect CallFire to Pydantic AI to validate every message payload before it sends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallFire MCP to Pydantic AI

Create your Vinkius account to connect CallFire 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 CallFire with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe CallFire MCP integration

When your agent decides to use `send_sms` or `send_voice_call`, Pydantic AI validates the exact payload structure. If the model hallucinates a phone number format or forgets a required text field, the execution fails loudly with a validation error. Developers fix the problem instead of sending garbage data to customers. The framework guarantees that the inputs match the MCP tool schema perfectly. You get production-grade reliability regardless of which underlying LLM you choose to power the agent.

Strict Log Ingestion

Your agent calls `list_calls` and `list_sent_sms` to retrieve campaign histories into predictable data structures. Pydantic AI ensures the incoming JSON matches your expected types, so your downstream Python code never crashes on a missing key. Specific transaction checks work the same way. The agent hits `get_call_details` or `get_sms_details` to investigate failed deliveries. Because the types are strict, you can safely pipe this error data directly into your internal dashboards.

Predictable Asset Management

The agent uses `list_keywords` to find available short codes and `list_campaign_sounds` to grab audio IDs. The framework catches any hallucinated IDs before the agent tries to attach them to a new campaign. Infrastructure monitoring stays reliable. Your code triggers `get_account_info` and `list_webhooks` to verify account health. Since Pydantic AI is model-agnostic, you can swap from OpenAI to a local model without rewriting your CallFire tool logic.

Setup guide

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

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

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

Instantiate an `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this into the `toolsets` array when defining your Agent. Do not use the deprecated `MCPServerHTTP` class.

Yes, it validates the payload schema against the tool definition. If the `send_sms` tool requires a specific string format for the destination number, Pydantic AI enforces it at runtime.

Yes, you can. The framework is completely model-agnostic. You can run a local Llama model and still give it full access to trigger voice calls through the MCP tools.

The framework throws a strict validation error. Your application catches this immediately rather than passing malformed delivery metrics from `list_calls` into your database.

Vinkius processes your CallFire MCP traffic through ephemeral, stateless sandboxes. Audio file IDs, webhook URLs, and account balances are processed in memory and immediately wiped. No persistent storage is ever attached to your server instance.

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