How to Use the zipperHQ MCP in LangChain

Q: How do I check connectivity status with zipperHQ using LangChain?

Call checkzipperstatus first. This verifies that your MCP Server connection is active and ready to run any subsequent tools. It's a quick sanity check, making sure the entire communication pipeline works before you start building complex chains.

Q: What data types can zipperHQ provide via LangChain?

The MCP Server provides contact information (via listcontacts), video metadata (via getvideo), and usage metrics like view counts. These are all key pieces of communication data. Your agent treats these structured outputs as reliable inputs for the next step in your chain.

Q: Can I search videos with zipperHQ using LangChain?

Absolutely. Run searchvideos and pass a keyword. The resulting list of matching videos can then be used to pull specific analytics. This two-step process ensures the chain finds exactly what you're looking for, saving time.

Q: What if I need account details with zipperHQ using LangChain?

Just call getaccount. This pulls your core ZipperHQ account information directly into your workflow. Having this foundational data lets the agent contextually adjust its actions, knowing who it's working for.

Q: Is video analytics available with zipperHQ using LangChain?

Yep. You use getvideoanalytics and pass a specific video ID. This returns deep performance data. This lets your agent make decisions based on actual user behavior, not guesswork.

Chain complex multi-step video communication workflows using LangChain.

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 LangChain

Create your Vinkius account to connect zipperHQ to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Contact Video Views

Use `get_contact_views` to pull specific metrics for any contact. This tells your agent exactly how many times a recipient viewed the content. You can then pass that data into other tools, like `search_videos`, allowing the chain to filter videos based on view counts and surface the most relevant material.

List And Analyze Videos

The `list_videos` tool gives you a full roster of video emails. From that list, your agent can pick one up and use `get_video_analytics` to get detailed performance stats. This pattern lets the chain not just find videos, but immediately assess which ones are performing best based on real metrics.

Manage Contacts & Recordings

Start by running `list_contacts` to map out all your recipients. Next, you can run `list_recordings` to see every screen recording made. This workflow lets the agent build a holistic picture: who was contacted, and what kind of content (video or recording) went out.

Setup guide

Set up zipperHQ MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes zipperHQ tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "zipperhq-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent zipperHQ transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Call `check_zipper_status` first. This verifies that your MCP Server connection is active and ready to run any subsequent tools. It's a quick sanity check, making sure the entire communication pipeline works before you start building complex chains.

The MCP Server provides contact information (via `list_contacts`), video metadata (via `get_video`), and usage metrics like view counts. These are all key pieces of communication data. Your agent treats these structured outputs as reliable inputs for the next step in your chain.

Absolutely. Run `search_videos` and pass a keyword. The resulting list of matching videos can then be used to pull specific analytics. This two-step process ensures the chain finds exactly what you're looking for, saving time.

Just call `get_account`. This pulls your core ZipperHQ account information directly into your workflow. Having this foundational data lets the agent contextually adjust its actions, knowing who it's working for.

Yep. You use `get_video_analytics` and pass a specific video ID. This returns deep performance data. This lets your agent make decisions based on actual user behavior, not guesswork.

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