How to Use the FileStack MCP in Pydantic AI

Q: How does Pydantic AI validate FileStack metadata?

When your agent calls getmetadata, the response is parsed through your Pydantic AI schema. This ensures the file properties conform to your exact Python type hints.

Q: Can I use FileStack OCR with Pydantic AI safely?

Yes, calling getocr returns raw text that Pydantic AI can validate against your custom document models. This prevents your agent from processing badly structured OCR outputs.

Q: How do I initialize the FileStack toolset?

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. This registers all eight tools, including generatetransformurl, in a single line of code.

Type-safe file processing and OCR extraction for your Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FileStack MCP to Pydantic AI

Create your Vinkius account to connect FileStack 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 FileStack with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe file ingestion for Pydantic AI

Ingest assets with confidence by calling `upload_from_url` to store files in FileStack. Because Pydantic AI enforces strict types, the resulting file identifiers are validated immediately, preventing malformed strings from breaking your pipeline. Your agent can then safely call `get_metadata` to extract file properties. The returned dictionary is parsed against your Pydantic models at runtime, ensuring that if a field is missing, your system fails loudly instead of corrupting data.

Strict validation of image analysis and OCR

When extracting text with `get_ocr` or analyzing images with `get_image_tags`, you cannot afford hallucinated data. This MCP Server ensures that the structured JSON returned by FileStack matches your schema exactly. You can also call `get_sfw_status` to verify safety scores before displaying user uploads. If the safety payload deviates from the expected schema, Pydantic AI catches the error instantly, keeping your UI clean and secure.

Validated video transcoding pipelines

Manage asynchronous video processing by triggering `start_video_transcode`. The returned UUID is strictly validated by your Pydantic AI agent, meaning you never pass a malformed job ID to your polling functions. The agent then polls `get_video_status` until the job completes. Once finished, you can safely generate delivery URLs using `generate_transform_url`, with all query parameters validated against your application's type definitions.

Setup guide

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

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

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

When your agent calls `get_metadata`, the response is parsed through your Pydantic AI schema. This ensures the file properties conform to your exact Python type hints.

Yes, calling `get_ocr` returns raw text that Pydantic AI can validate against your custom document models. This prevents your agent from processing badly structured OCR outputs.

Use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. This registers all eight tools, including `generate_transform_url`, in a single line of code.

If the FileStack MCP Server returns data that violates your model, Pydantic AI raises a validation error. This prevents silent failures and ensures your database only receives clean data.

Your media data, including images, videos, and raw OCR text, is processed inside an ephemeral sandbox. No data is stored or logged on the MCP host, ensuring complete compliance with your data privacy standards.

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