Can I trigger auto-transcription for a video using the agent?

Yes! Use the `transcribe_video` tool with the Project ID. Your agent will trigger CaptionHub's AI engine to start transcribing the video content instantly.

How do I get the download link for finished subtitles?

Simply ask the agent to `export_captions` and provide the Project ID and the language code (e.g., 'fr' or 'es'). It will return the export URL for your finished caption set.

Does the integration allow approving captions via the workspace?

Yes. Use the `approve_captions` tool with the Project ID and Language. This will mark the specific caption set as approved in your CaptionHub workflow.

CaptionHub MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: CaptionHub
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect CaptionHub through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to CaptionHub "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in CaptionHub?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About CaptionHub MCP Server

Connect your CaptionHub account to any AI agent and orchestrate your video localization, AI-powered transcription, and subtitle approval workflows through natural conversation.

Pydantic AI validates every CaptionHub tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Project Oversight — List all localization projects and retrieve detailed metadata, including source and target languages.
Automated Transcription — Trigger AI-powered auto-transcription for your video assets directly from your workspace.
Caption Lifecycle — Handover, approve, or archive caption sets for specific languages using natural language.
Export Coordination — Retrieve export links for finished captions in various formats straight from your workspace.
Workflow Automation — Monitor active webhooks and project statuses to ensure your localization pipeline is efficient.
Data Deep Dives — Get detailed data for specific project, caption, or user IDs using natural language.

The CaptionHub MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect CaptionHub to Pydantic AI via MCP

Follow these steps to integrate the CaptionHub MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from CaptionHub with type-safe schemas

Why Use Pydantic AI with the CaptionHub MCP Server

Pydantic AI provides unique advantages when paired with CaptionHub through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your CaptionHub integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your CaptionHub connection logic from agent behavior for testable, maintainable code

CaptionHub + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the CaptionHub MCP Server delivers measurable value.

Type-safe data pipelines: query CaptionHub with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple CaptionHub tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query CaptionHub and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock CaptionHub responses and write comprehensive agent tests

CaptionHub MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect CaptionHub to Pydantic AI via MCP:

approve_captions

Approve a caption set for a specific language

archive_project

Archive a project permanently

create_project

Create a new captioning project

export_captions

Get the export URL for a caption set

get_account_info

Retrieve core account information

get_project_details

Get details of a specific project

list_projects

List all video captioning projects

list_webhooks

List all active webhooks

transcribe_video

Trigger AI auto-transcription for a project

update_project

Update project metadata

Example Prompts for CaptionHub in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with CaptionHub immediately.

"List all my current video projects in CaptionHub."

"Start auto-transcription for the 'Product Keynote' project."

"Get the French subtitle export link for project proj_123."

Troubleshooting CaptionHub MCP Server with Pydantic AI

Common issues when connecting CaptionHub to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

CaptionHub + Pydantic AI FAQ

Common questions about integrating CaptionHub MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your CaptionHub MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.