How to Use the Fliki (AI Text-to-Video & Speech API) MCP in Pydantic AI

Q: How do I register the Fliki (AI Text-to-Video & Speech API) MCP Server inside Pydantic AI?

Install the slim package with MCP support, instantiate MCPToolset with the server's HTTP URL, and pass it to your Agent in the toolsets parameter.

Q: Is the MCPServerHTTP class still used in the latest setup?

No, that class is deprecated. You should use the unified MCPToolset class to connect to the external MCP server.

Build type-safe video pipelines with Pydantic AI, validating script schemas and voice configurations at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fliki (AI Text-to-Video & Speech API) MCP to Pydantic AI

Create your Vinkius account to connect Fliki (AI Text-to-Video & Speech API) 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 Fliki (AI Text-to-Video & Speech API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Schema Validation for `generate_video`

Stop worrying about your model sending malformed payloads to the video generator. Pydantic AI validates every argument passed to `generate_video` at runtime, ensuring aspect ratios and background music options match the exact schema before hitting the server. If the model attempts to pass an invalid parameter, the system raises a validation error immediately. This prevents wasted API calls and keeps your automated video generation pipeline robust and predictable.

Type-Safe Voice Discovery with Pydantic AI

Querying available voices is completely type-safe with this MCP Server. When your agent calls `list_voices`, the returned list of speakers is validated against strict Pydantic models, protecting your downstream application from unexpected schema changes. This setup works regardless of which LLM you use. Whether you run Gemini, Claude, or a local model, the framework guarantees that the voice data returned to your agent is clean and structured.

Tracking Renders without Silent Failures

Tracking video rendering status can be fragile when dealing with raw HTTP responses. Your agent uses `get_video` to fetch the status, and the framework validates the response to ensure you get a clean download link and progress state. You configure this by passing the `MCPToolset` pointing to the external server directly to your `Agent` constructor. This unified approach handles the underlying SSE or HTTP transport connections safely.

Setup guide

Set up Fliki (AI Text-to-Video & Speech API) 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": {
        "fliki-ai-text-to-video-speech-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Fliki (AI Text-to-Video & Speech API) tools.",
)

result = await agent.run("List recent Fliki (AI Text-to-Video & Speech API) 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 Fliki. 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 Fliki (AI Text-to-Video & Speech API) 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 Fliki (AI Text-to-Video & Speech API) MCP in Pydantic AI

Install the slim package with MCP support, instantiate `MCPToolset` with the server's HTTP URL, and pass it to your `Agent` in the `toolsets` parameter.

The framework will immediately raise a validation error instead of passing corrupt data to your agent. This ensures your code fails loudly and safely.

Yes, the framework is completely model-agnostic. You can pair this server with local models or commercial APIs while retaining full schema validation.

No, that class is deprecated. You should use the unified `MCPToolset` class to connect to the external MCP server.

All script payloads and voice selections are processed inside an ephemeral, zero-trust V8 Isolate Sandbox. Vinkius manages the authentication token securely, ensuring your raw content is never persisted on the server after the video generation completes.

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