How to Use the MiiTel MCP in Pydantic AI

Q: What happens in Pydantic AI if the MiiTel API changes its response format?

Pydantic AI will raise a validation error the moment listcalls or getcalldetails returns data that violates your schema. This prevents your agent from hallucinating based on malformed MiiTel API payloads.

Q: How does Pydantic AI parse MiiTel call sentiment scores?

The Pydantic AI agent pulls call data via getcalldetails and parses the sentiment metrics directly into a typed schema. This ensures your coaching logic always receives valid numeric scores and clean text strings from MiiTel.

Q: How is my MiiTel customer data secured in Pydantic AI?

Your synced contacts from listsyncedcontacts are validated locally in memory using Python type hints. Pydantic AI does not cache or store your MiiTel customer phone numbers or call logs on external servers.

Ensure type-safe sales coaching pipelines with Pydantic AI and MiiTel.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MiiTel MCP to Pydantic AI

Create your Vinkius account to connect MiiTel 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 MiiTel with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe call tracking with Pydantic AI

The `list_calls` tool returns structured MiiTel call histories that Pydantic AI validates against strict schemas at runtime via this MCP Server. If the MiiTel API returns an unexpected payload structure, your Pydantic AI agent fails instantly rather than outputting corrupted analysis. This strict validation also applies to `get_call_details` when fetching MiiTel sentiment scores. Your Pydantic AI agent can confidently parse sentiment scores and call quality metrics knowing that every field matches your exact Python type definitions.

Validate meeting metadata before processing

The `list_online_meetings` tool lets your agent pull meeting histories from MiiTel via this MCP Server with guaranteed schema compliance. Pydantic AI inspects the incoming MiiTel data to ensure all dates, durations, and participant counts conform to your models. When drilling down with `get_meeting_details`, the Pydantic AI agent maps the MiiTel response directly to type-safe Python objects. This prevents runtime errors when your agent generates automated coaching summaries from MiiTel meeting logs.

Enforce schema integrity on CRM contacts

The `list_synced_contacts` tool retrieves your MiiTel customer database while enforcing strict data types through Pydantic AI. Any missing phone numbers or malformed emails in your MiiTel contacts are caught before they reach your LLM. By matching these validated contacts with your team roster from `list_miitel_users`, you can build reliable MiiTel attribution pipelines. The Pydantic AI toolset approach ensures that your agent operates only on clean, verified sales data.

Setup guide

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

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

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

Create an instance of MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset directly into your Pydantic AI Agent constructor to give your LLM type-safe access to all MiiTel call and meeting tools.

Pydantic AI will raise a validation error the moment list_calls or get_call_details returns data that violates your schema. This prevents your agent from hallucinating based on malformed MiiTel API payloads.

Yes, Pydantic AI is model-agnostic. You can connect the MCP toolset to run list_online_meetings and analyze the MiiTel data using OpenAI, Anthropic, or local models like Llama.

The Pydantic AI agent pulls call data via get_call_details and parses the sentiment metrics directly into a typed schema. This ensures your coaching logic always receives valid numeric scores and clean text strings from MiiTel.

Your synced contacts from list_synced_contacts are validated locally in memory using Python type hints. Pydantic AI does not cache or store your MiiTel customer phone numbers or call logs on external 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