How to Use the Tolstoy MCP in Pydantic AI

Q: How do I list all video projects using Tolstoy with Pydantic AI?

You use listinteractiveprojects to get a validated list of all your shoppable video funnels. Because the response is strictly typed, you know exactly what fields you're working with.

Q: Can I list all videos using Tolstoy with Pydantic AI?

Yes, listvideos returns a strictly typed list of content. This guarantees that when your agent processes the video metadata, it won't encounter any unexpected data types.

Q: Does the MCP Server handle webhooks with Tolstoy and Pydantic AI?

The listwebhooks tool lets your agent see all configured endpoints. Furthermore, if webhook payloads are passed through the server, Pydantic validates their structure before they're used.

Q: What happens when I use Tolstoy with Pydantic AI?

When you call any tool, like getvideoanalytics, the MCP Server ensures the response conforms to your defined models. You get guaranteed correctness every time your agent runs.

Run shoppable video funnels with Pydantic AI. Ensure flawless data handling for e-commerce experiences.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tolstoy MCP to Pydantic AI

Create your Vinkius account to connect Tolstoy 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 Tolstoy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Video Performance Metrics

The `get_video_analytics` tool provides performance metrics, but Pydantic validates the output structure instantly. This means your agent gets predictable data every time. If the API response is messy, the failure is loud and clear. You never deal with corrupted or unexpected video data fields.

Manage Video Content Assets

To manage content, use `list_videos` to get a schema-validated list of all assets. This ensures every video record has the expected metadata. Need to add something? Calling `upload_video` means your agent only proceeds if the data structure is correct from the start.

List and Control Folders

The `list_folders` tool gives you a validated list of all video folder paths. This allows your agent to precisely map out where specific types of content should live. This control over structure makes building complex, multi-step funnels much safer for the agent.

Setup guide

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

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

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

You use `list_interactive_projects` to get a validated list of all your shoppable video funnels. Because the response is strictly typed, you know exactly what fields you're working with.

The server handles video performance metrics and webhook configurations. The strength of the MCP Server here is validating these complex data structures at runtime for maximum reliability.

Yes, `list_videos` returns a strictly typed list of content. This guarantees that when your agent processes the video metadata, it won't encounter any unexpected data types.

The `list_webhooks` tool lets your agent see all configured endpoints. Furthermore, if webhook payloads are passed through the server, Pydantic validates their structure before they're used.

When you call any tool, like `get_video_analytics`, the MCP Server ensures the response conforms to your defined models. You get guaranteed correctness every time your agent runs.

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