How to Use the Cloudflare Stream MCP in Pydantic AI

Q: Can I use Pydantic AI to list Cloudflare Stream watermarks?

Yes, your agent calls listwatermarks to retrieve your profile settings. The result is validated against your schema to ensure the watermark configuration is correct.

Build type-safe video management workflows using Pydantic AI and the Cloudflare Stream MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloudflare Stream MCP to Pydantic AI

Create your Vinkius account to connect Cloudflare Stream 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 Cloudflare Stream with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate video operations in Pydantic AI

Every tool response like `list_signing_keys` is checked against your Pydantic schemas. If the API returns malformed data, your agent stops immediately. This prevents your agent from processing corrupted metadata. You get a clean validation error instead of silent logic failures.

Automate caption uploads in Pydantic AI

Your agent prepares VTT files and sends them using `upload_caption`. Because you use Pydantic models, the file metadata is verified before it leaves your system. This guarantees that only correctly formatted caption files reach your video infrastructure. It eliminates errors caused by invalid subtitle data.

Configure webhooks using Pydantic AI

Your agent maintains your integration health by calling `get_webhook` and `update_webhook`. It ensures your notification endpoints stay in sync with your infrastructure. If the configuration deviates from your required schema, the agent detects the mismatch. It then applies the necessary updates to correct the webhook settings.

Setup guide

Set up Cloudflare Stream 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": {
        "cloudflare-stream-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

The MCP toolset automatically maps API responses to your defined Pydantic models. Any field mismatch triggers a runtime exception to keep your agent state consistent.

Yes, your agent calls `list_watermarks` to retrieve your profile settings. The result is validated against your schema to ensure the watermark configuration is correct.

Yes, every tool call is wrapped in a type-safe interface. Your agent refuses to execute any operation that does not meet the strict input requirements defined in the schema.

Yes, you can configure the MCP toolset to use SSE or Streamable HTTP. This allows your agent to maintain a persistent connection to the server.

The server only handles webhook URLs and video metadata identifiers. All traffic is transient and protected by the transport layer security of your local environment.

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