How to Use the Thoughtly MCP in Pydantic AI

Q: How does Pydantic AI connect to the Thoughtly MCP Server?

You'll use the MCPToolset from the pydantic-ai-slim library, passing it your Vinkius server URL. Then, you provide that toolset to your agent. It's a clean, unified way to add external tools.

Q: What happens if the Thoughtly API returns bad data to my Pydantic AI agent?

Your agent will raise a ValidationError immediately. This is the main benefit of using Pydantic AI: it prevents bad data from propagating through your system. You'll know exactly where and why the data structure was wrong.

Add type-safe, reliable voice automation to your app with Pydantic AI and Thoughtly. Correctness guaranteed.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Thoughtly MCP to Pydantic AI

Create your Vinkius account to connect Thoughtly to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Thoughtly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build a CRM with a Guaranteed Schema

Manage your contacts with the confidence that your data structures are always correct. Your agent can add a person with `create_contact` or fetch your whole list via `list_contacts`. If the Thoughtly server ever returns a field that doesn't match your Pydantic model, your code will raise an error immediately. This strictness applies to all CRUD operations. When your agent runs `update_contact`, `get_contact`, or `delete_contact`, Pydantic AI validates the response. No more silent data corruption or dealing with unexpected `null` values from an API.

Trigger Calls with Validated Responses

Make calls programmatically and trust the results. Your agent uses `trigger_call` to start a phone call. The real power here is knowing the response object confirming the call was initiated will always match your defined Pydantic model. After a call, you can review what happened with total type safety. Your agent can fetch call logs using `list_calls`, and then get a specific transcript and details with `get_call_history`. Every field in the response is validated, so your agent won't crash on malformed data.

A Type-Safe MCP Server for Pydantic AI

Your agent needs to know who it is and what it can do. `get_user` provides the agent's profile, and `list_interviews` shows the available voice agent configurations. Pydantic AI ensures these introspection calls return predictable, typed objects. Before choosing a voice, your agent can use `get_interview` to fetch the details of a specific voice persona. This is yet another interaction where Pydantic AI protects you from runtime surprises. This MCP Server respects your data models.

Setup guide

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

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

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

You'll use the `MCPToolset` from the `pydantic-ai-slim` library, passing it your Vinkius server URL. Then, you provide that toolset to your agent. It's a clean, unified way to add external tools.

Your agent will raise a `ValidationError` immediately. This is the main benefit of using Pydantic AI: it prevents bad data from propagating through your system. You'll know exactly where and why the data structure was wrong.

Yes. Pydantic AI is model-agnostic, so you can use it with OpenAI, Gemini, or a model running on your own machine. The Thoughtly tools will work the same way regardless of which LLM you choose to power your agent.

Yes, the server supports Streamable HTTP and SSE transports. You can configure your `MCPToolset` to use streaming, which allows your Pydantic AI agent to process responses as they arrive instead of waiting for the full payload.

The server is designed to be stateless. It processes contact records and call transcripts only when a tool is invoked. Each request runs in a fresh, sandboxed environment on Vinkius and is torn down afterward, ensuring your data isn't persisted.

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