How to Use the zipperHQ MCP in Pydantic AI

Q: Can I check API connectivity with zipperHQ using Pydantic AI?

Yes. You can call checkzipperstatus to confirm the server's operational status before running any mission-critical tasks, guaranteeing your agent starts clean.

Q: How do I list all my screen recordings using zipperHQ and Pydantic AI?

The listrecordings tool fetches the session data. Because you're running through a typed framework, you know exactly what fields to expect for every single recording listed.

Ensure video communication integrity with Pydantic AI and the 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 zipperHQ MCP to Pydantic AI

Create your Vinkius account to connect zipperHQ 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 zipperHQ with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validated Video Analytics

The `get_video_analytics` tool retrieves metrics, but because you're using Pydantic AI, you get a guaranteed data structure back. The agent fails loudly if the API returns anything unexpected. You can also reliably pull general video details by calling `get_video`. This level of type-safety is non-negotiable for production code.

Validated Contact Management

Run `list_contacts` to get a roster. The agent validates this list against your Pydantic model, ensuring every field—like the contact name or ID—is exactly what you expect. Want to check view counts? Calling `get_contact_views` returns data that is rigorously checked at runtime.

Validated Content Discovery

Need content fast? The agent executes `search_videos`, and the resulting list is immediately validated. You don't have to worry about missing fields or corrupted records. For a complete view, you can use `list_videos` to get all video email metadata, knowing that every field passed back has been type-checked.

Setup guide

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

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

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

Every piece of data returned by the MCP Server—whether it's a contact ID or an analytics score—is validated against your defined Pydantic models. If the API messes up, your agent throws an error, not bad data.

This MCP Server handles video communication metadata, including contact lists (`list_contacts`), specific view counts, and general video details. The focus is on making this messaging data correct.

Yes. You can call `check_zipper_status` to confirm the server's operational status before running any mission-critical tasks, guaranteeing your agent starts clean.

The security relies on type validation. This means that even if the network layer is fine, the *structure* of the data must be perfect for your agent to proceed.

The `list_recordings` tool fetches the session data. Because you're running through a typed framework, you know exactly what fields to expect for every single recording listed.

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