How to Use the CaptionHub MCP in Pydantic AI

Bring type-safe runtime validation to your CaptionHub workflows using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CaptionHub MCP to Pydantic AI

Create your Vinkius account to connect CaptionHub 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 CaptionHub with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe video localization via MCP Server.

Stop worrying about silent API failures when your agent calls `list_projects` or `get_project_details`. Pydantic AI validates the response against strict schemas immediately. If the localization server returns unexpected fields, your Python application fails loudly and immediately. This keeps your video database clean and prevents corrupted metadata from spreading.

Strict validation for caption approvals.

The `approve_captions` tool lets you automate localization sign-offs with complete confidence. Your agent handles the approvals, ensuring the payload matches your production types. By using this MCP Server, you gain a strict layer of type safety. Your agent cannot accidentally pass invalid language codes or malformed project IDs to the server.

Programmatic video transcription pipelines.

Run your automated transcription steps via `transcribe_video` and check account limits with `get_account_info`. Every returned integer, string, and list is validated at the runtime boundary. You can use local models or commercial APIs. The underlying tool execution remains strictly typed.

Setup guide

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

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

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

Install the slim package with the MCP extra, instantiate the toolset with your Vinkius HTTP URL, and pass it to your Agent.

The framework validates all incoming tool data at runtime. If something is off, it raises a validation error immediately.

Yes, your agent can call the export tool to retrieve the download URL. The response schema is fully validated.

The unified toolset class supports both streamable HTTP and SSE transports for connecting to external MCP servers.

Your caption text, project structures, and account settings are processed through secure, ephemeral V8 isolates on Vinkius. No data is cached or stored long-term.

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