How to Use the Ziflow MCP in LangChain

Q: How do I use Ziflow with LangChain to find proof details?

You use searchproofs first; that gives you the list of relevant proofs. Then, your agent uses getproof on a specific ID from that list. This provides all the necessary metadata for further analysis.

Q: How do I list all active webhooks with Ziflow and LangChain?

You simply call the listwebhooks tool. The output gives you a clean list of every webhook currently configured on your account, letting you audit what's connected.

Q: If I need to verify contact information with Ziflow and LangChain, which tools do I use?

You should start by calling getcontactbyemail. This tool takes an email address as input and returns the corresponding contact profile. It’s a direct lookup for user identity.

Build complex content review pipelines with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ziflow MCP to LangChain

Create your Vinkius account to connect Ziflow 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 Ziflow with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step proof workflows.

You start by searching for proofs using `search_proofs`. The resulting list of IDs then lets your agent retrieve specific details via `get_proof`. This chain structure allows the agent to pass the full proof data into a final step, like generating a review link with `get_proof_viewer_url`, all in one go.

Manage user access and folders.

The agent first pulls a list of all available team members using `list_team_users`. It can then use the resulting user IDs to check which proof folders exist by calling `list_folders`. This sequence lets you build logic: if a specific user isn't in the team, or if their folder doesn't exist, the whole chain fails gracefully.

Verify contact and account status.

To kick things off, your agent first gathers general company details using `get_account_info`. Next, it runs a targeted lookup to find a specific person's profile using `get_contact_by_email`. This setup lets the chain check if a user exists and what their basic account parameters are before proceeding with any core content actions.

Setup guide

Set up Ziflow 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 Ziflow 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({
    "ziflow-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 Ziflow 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 Ziflow. 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 Ziflow 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 Ziflow MCP in LangChain

You use `search_proofs` first; that gives you the list of relevant proofs. Then, your agent uses `get_proof` on a specific ID from that list. This provides all the necessary metadata for further analysis.

This server touches account profile and team member identity data. When running a chain, you're working with structured information about who the users are within your organization.

Absolutely. You can set up a multi-step process where an agent retrieves proof data via `get_proof` and then uses that information as the input for `submit_decision`. This simulates a full sign-off workflow.

You simply call the `list_webhooks` tool. The output gives you a clean list of every webhook currently configured on your account, letting you audit what's connected.

You should start by calling `get_contact_by_email`. This tool takes an email address as input and returns the corresponding contact profile. It’s a direct lookup for user identity.

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