How to Use the Spiritme MCP in Pydantic AI

Q: How does Spiritme ensure reliable video generation with Pydantic AI?

The MCP Server guarantees that the output of generatevideo adheres to a strict, predefined schema. Your agent doesn't just 'hope' the data is right; it verifies the structure against your models.

Q: Can I list all available voices with Spiritme and Pydantic AI?

Yes, using listvoices. Because of Pydantic validation, you'll receive a clean, predictable list where every voice object has the exact fields your agent expects.

Q: What if I need to delete video metadata with Spiritme and Pydantic AI?

Use deletevideo. The process is wrapped in type checking. Your agent receives a validated response confirming the deletion, which is critical for maintaining accurate records.

Q: Does Spiritme support generating audio components with Pydantic AI?

It does. generateaudio returns structured data detailing the audio file's location and parameters. This makes it easy for your agent to consume the output reliably.

Q: What data privacy assurances are provided when using Spiritme and Pydantic AI?

The MCP Server handles video metadata. The system confirms that all returned job and asset identifiers are strictly typed, ensuring only necessary IDs leave the processing context.

Guaranteed data correctness for video generation using Pydantic AI. Type-safe results every time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Spiritme MCP to Pydantic AI

Create your Vinkius account to connect Spiritme 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 Spiritme with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate all MCP Server calls.

The core power here is that your agent doesn't trust the API response; it validates it. If `get_avatar` returns fields in an unexpected format, the agent fails immediately with a specific Pydantic validation error. No silent corruption, ever. This type-safe approach means you know exactly what data structure you're dealing with—it’s correct or the system throws a clear exception.

Get structured asset details.

Retrieving assets is rock solid. Functions like `get_voice` and `list_templates` return objects that conform to strict Python models. You'll get predictable data on every call, whether it’s a voice profile or a template list. This type safety saves huge amounts of time debugging messy API responses.

Manage content lifecycles safely.

Managing video assets is straightforward and reliable. When you call `delete_video`, the function returns a validated confirmation object, so your agent knows definitively that the cleanup succeeded or failed. Similarly, calling `get_job_status` gives you structured status data, letting your agent build complex logic around success/failure states.

Setup guide

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

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

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

The MCP Server guarantees that the output of `generate_video` adheres to a strict, predefined schema. Your agent doesn't just 'hope' the data is right; it verifies the structure against your models.

Yes, using `list_voices`. Because of Pydantic validation, you'll receive a clean, predictable list where every voice object has the exact fields your agent expects.

Use `delete_video`. The process is wrapped in type checking. Your agent receives a validated response confirming the deletion, which is critical for maintaining accurate records.

It does. `generate_audio` returns structured data detailing the audio file's location and parameters. This makes it easy for your agent to consume the output reliably.

The MCP Server handles `video metadata`. The system confirms that all returned job and asset identifiers are strictly typed, ensuring only necessary IDs leave the processing context.

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