How to Use the CallGear MCP in Pydantic AI

Q: How do I configure the CallGear MCP Server with Pydantic AI?

Instantiate MCPToolset with your Vinkius HTTP URL and pass it to the toolsets argument of your Agent. Do not use the deprecated MCPServerHTTP class.

Q: Does Pydantic AI support SSE transports for this MCP Server?

Yes, the MCPToolset class supports both Streamable HTTP and SSE transports. This allows you to connect to your externally hosted CallGear server.

Run type-safe CallGear data validation in your Pydantic AI workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallGear MCP to Pydantic AI

Create your Vinkius account to connect CallGear 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 CallGear with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Communication Audits in Pydantic AI

The `get_communications_report` tool fetches multi-channel interaction histories and validates them against strict runtime schemas using Pydantic AI. If the API returns unexpected formats or missing fields, the framework raises an immediate validation error instead of passing bad data to your model. You register this capability by passing the `MCPToolset` instance directly into your `Agent` definition. This ensures that every call, chat, or email record matches your exact Python type hints before the agent processes it.

Validate Call Scenarios via this MCP Server

The `list_call_scenarios` tool lists your active phone routing rules and maps them to Pydantic models at runtime. This MCP Server guarantees that your agent receives structured configuration objects, eliminating silent failures when analyzing routing logic. Your agent can cross-reference these scenarios with `list_tags` to ensure call handlers tag conversations correctly. Because Pydantic AI is model-agnostic, you can run this validation pipeline using any LLM provider.

Strict Reporting of Site Statistics

The `get_site_daily_stats` tool retrieves daily performance data, forcing the agent to process web metrics under strict type constraints. If your agent attempts to calculate conversion rates with malformed strings, Pydantic AI halts execution immediately. To set this up, install `pydantic-ai-slim[mcp]` and connect to the external Vinkius HTTP endpoint. This keeps your runtime lightweight while maintaining complete type safety across your marketing automation stack.

Setup guide

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

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

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

Instantiate `MCPToolset` with your Vinkius HTTP URL and pass it to the `toolsets` argument of your `Agent`. Do not use the deprecated `MCPServerHTTP` class.

The framework raises a validation error at runtime. This prevents your agent from processing corrupt call reports or hallucinating values based on bad inputs.

Yes, the `MCPToolset` class supports both Streamable HTTP and SSE transports. This allows you to connect to your externally hosted CallGear server.

Yes, Pydantic AI is model-agnostic. You can run your CallGear tool validation pipelines using Anthropic, Gemini, or local models.

Your account information and user lists are validated entirely in your local memory space. The HTTP connection to the Vinkius endpoint uses standard token authentication, and no data is cached on Vinkius servers.

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